#27 by GitHub stars
mem0ai/mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
integrations/antigravity-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/antigravity-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/antigravity-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/antigravity-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/antigravity-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/antigravity-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/claude-code-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/codex-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/cursor-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/kimi-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/pause/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/resume/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/mem0-agent-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/openclaw/skills/memory-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-context-loader/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-scope/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/opencode-plugin/opencode-skills/mem0-tour/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/context-loader/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/forget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/remember/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/status/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
integrations/pi-agent-plugin/skills/tour/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0-integrate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0-oss-to-platform/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0-test-integration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
skills/mem0-vercel-ai-sdk/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
26cdefb46600 → ed1f10fc8708
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 26cdefb46600
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit ed1f10fc87080f0b67f99be370817504888462ab
git clone --filter=blob:none --no-checkout https://github.com/mem0ai/mem0.git .hotskills/mem0ai-mem0 && git -C .hotskills/mem0ai-mem0 checkout --detach ed1f10fc87080f0b67f99be370817504888462ab
# Copy each selected skill directory from .hotskills/mem0ai-mem0 into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/mem0ai/mem0.git .hotskills/mem0ai-mem0 && git -C .hotskills/mem0ai-mem0 checkout --detach ed1f10fc87080f0b67f99be370817504888462ab
# Copy each selected skill directory from .hotskills/mem0ai-mem0 into .agents/skills/<skill-name>/68.5kGitHub stars
413stars in 7 days
56skills in this repository
10commits in 30 days
Heat
6.5- Star growth, last 7 daysAhead of 76% of tracked repositories
- Star growth, last 24 hoursAhead of 69% of tracked repositories
- Rank movement, last 7 daysAhead of 74% of tracked repositories
- Commits, last 30 daysAhead of 77% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- forget
integrations/antigravity-plugin/skills/forget - pause
integrations/antigravity-plugin/skills/pause - remember
integrations/antigravity-plugin/skills/remember - resume
integrations/antigravity-plugin/skills/resume - search
integrations/antigravity-plugin/skills/search - status
integrations/antigravity-plugin/skills/status - forget
integrations/claude-code-plugin/skills/forget - pause
integrations/claude-code-plugin/skills/pause - remember
integrations/claude-code-plugin/skills/remember - resume
integrations/claude-code-plugin/skills/resume - search
integrations/claude-code-plugin/skills/search - status
integrations/claude-code-plugin/skills/status - forget
integrations/codex-plugin/skills/forget - pause
integrations/codex-plugin/skills/pause - remember
integrations/codex-plugin/skills/remember - resume
integrations/codex-plugin/skills/resume - search
integrations/codex-plugin/skills/search - status
integrations/codex-plugin/skills/status - forget
integrations/cursor-plugin/skills/forget - pause
integrations/cursor-plugin/skills/pause - remember
integrations/cursor-plugin/skills/remember - resume
integrations/cursor-plugin/skills/resume - search
integrations/cursor-plugin/skills/search - status
integrations/cursor-plugin/skills/status - forget
integrations/kimi-plugin/skills/forget - pause
integrations/kimi-plugin/skills/pause - remember
integrations/kimi-plugin/skills/remember - resume
integrations/kimi-plugin/skills/resume - search
integrations/kimi-plugin/skills/search - status
integrations/kimi-plugin/skills/status - forget
integrations/mem0-agent-plugin/skills/forget - pause
integrations/mem0-agent-plugin/skills/pause - remember
integrations/mem0-agent-plugin/skills/remember - resume
integrations/mem0-agent-plugin/skills/resume - search
integrations/mem0-agent-plugin/skills/search - status
integrations/mem0-agent-plugin/skills/status - memory-triage
integrations/openclaw/skills/memory-triage - mem0-context-loader
integrations/opencode-plugin/opencode-skills/mem0-context-loader - mem0-forget
integrations/opencode-plugin/opencode-skills/mem0-forget - mem0-remember
integrations/opencode-plugin/opencode-skills/mem0-remember - mem0-scope
integrations/opencode-plugin/opencode-skills/mem0-scope - mem0-search
integrations/opencode-plugin/opencode-skills/mem0-search - mem0-status
integrations/opencode-plugin/opencode-skills/mem0-status - mem0-tour
integrations/opencode-plugin/opencode-skills/mem0-tour - context-loader
integrations/pi-agent-plugin/skills/context-loader - forget
integrations/pi-agent-plugin/skills/forget - remember
integrations/pi-agent-plugin/skills/remember - search
integrations/pi-agent-plugin/skills/search - status
integrations/pi-agent-plugin/skills/status - tour
integrations/pi-agent-plugin/skills/tour - mem0
skills/mem0 - mem0-cli
skills/mem0-cli - mem0-integrate
skills/mem0-integrate - mem0-oss-to-platform
skills/mem0-oss-to-platform - mem0-test-integration
skills/mem0-test-integration - mem0-vercel-ai-sdk
skills/mem0-vercel-ai-sdk
How it works
forget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
236 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../../../.claude-plugin/marketplace.jsonasset387 bytes../../hooks.jsonasset451 bytes../../hooks.jsonasset451 bytes../../hooks.jsonasset451 bytes../../hooks.jsonasset451 bytesSKILL.mdcore1,064 bytesSKILL.mdcore1,064 bytes../../../claude-code-plugin/.claude-plugin/plugin.jsonasset1,829 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../claude-code-plugin/hooks/hooks.jsonasset3,100 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../codex-plugin/hooks/hooks.jsonasset2,020 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes../../../cursor-plugin/hooks/hooks.jsonasset1,201 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${ANTIGRAVITY_PLUGIN_ROOT}/core/memory_cli.py" --harness "antigravity" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
181 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore772 bytesSKILL.mdcore772 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${ANTIGRAVITY_PLUGIN_ROOT}/core/memory_cli.py" --harness "antigravity" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore978 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
112 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore476 bytesSKILL.mdcore476 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${ANTIGRAVITY_PLUGIN_ROOT}/core/memory_cli.py" --harness "antigravity" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Antigravity sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
315 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,352 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
283 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,179 bytesSKILL.mdcore1,179 bytesSKILL.mdcore1,179 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${ANTIGRAVITY_PLUGIN_ROOT}/core/memory_cli.py" --harness "antigravity" status --json
python3 "${ANTIGRAVITY_PLUGIN_ROOT}/core/memory_cli.py" --harness "antigravity" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), sayforget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
244 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../../core/memory_cli.py
Files
../../core/memory_cli.pyruns5,348 bytesSKILL.mdcore1,100 bytesSKILL.mdcore1,100 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
189 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../../core/memory_cli.py
Files
../../core/memory_cli.pyruns5,348 bytesSKILL.mdcore808 bytesSKILL.mdcore808 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore978 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
120 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../../core/memory_cli.py
Files
../../core/memory_cli.pyruns5,348 bytesSKILL.mdcore512 bytesSKILL.mdcore512 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Claude Code sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
314 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,352 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Scripts executed separately
../../core/memory_cli.py
Files
../../core/memory_cli.pyruns5,348 bytesSKILL.mdcore1,251 bytesSKILL.mdcore1,251 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" status --json
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), sayforget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
237 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,080 bytesSKILL.mdcore1,080 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "codex" --plugin-data-dir "${PLUGIN_DATA}" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
182 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore788 bytesSKILL.mdcore788 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "codex" --plugin-data-dir "${PLUGIN_DATA}" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore978 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
113 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore492 bytesSKILL.mdcore492 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "codex" --plugin-data-dir "${PLUGIN_DATA}" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Codex sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
314 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,346 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
285 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,211 bytesSKILL.mdcore1,211 bytesSKILL.mdcore1,211 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "codex" --plugin-data-dir "${PLUGIN_DATA}" status --json
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "codex" --plugin-data-dir "${PLUGIN_DATA}" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), sayforget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
231 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,054 bytesSKILL.mdcore1,054 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${CURSOR_PLUGIN_ROOT}/core/memory_cli.py" --harness "cursor" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
176 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore762 bytesSKILL.mdcore762 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${CURSOR_PLUGIN_ROOT}/core/memory_cli.py" --harness "cursor" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore978 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
107 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore466 bytesSKILL.mdcore466 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${CURSOR_PLUGIN_ROOT}/core/memory_cli.py" --harness "cursor" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Cursor sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
313 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,347 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
273 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,159 bytesSKILL.mdcore1,159 bytesSKILL.mdcore1,159 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${CURSOR_PLUGIN_ROOT}/core/memory_cli.py" --harness "cursor" status --json
python3 "${CURSOR_PLUGIN_ROOT}/core/memory_cli.py" --harness "cursor" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), sayforget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
232 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,050 bytesSKILL.mdcore1,050 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${KIMI_PLUGIN_ROOT}/core/memory_cli.py" --harness "kimi" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
177 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore758 bytesSKILL.mdcore758 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${KIMI_PLUGIN_ROOT}/core/memory_cli.py" --harness "kimi" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore978 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
108 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore462 bytesSKILL.mdcore462 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${KIMI_PLUGIN_ROOT}/core/memory_cli.py" --harness "kimi" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Kimi sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
314 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,345 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
275 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,151 bytesSKILL.mdcore1,151 bytesSKILL.mdcore1,151 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${KIMI_PLUGIN_ROOT}/core/memory_cli.py" --harness "kimi" status --json
python3 "${KIMI_PLUGIN_ROOT}/core/memory_cli.py" --harness "kimi" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), sayforget
When your agent uses it
Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
222 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,022 bytesSKILL.mdcore1,022 bytes
Read SKILL.md
# Forget this repository's memories
This permanently deletes remote memories. Before running anything, tell the
user exactly what will be deleted: their own memories for this repository
only. The repository's project memory is shared by everyone who works in it,
so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, addpause
When your agent uses it
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
167 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore730 bytesSKILL.mdcore730 bytes
Read SKILL.md
# Pause memory capture
To pause (hooks stop capturing and sending session content; a minimal
telemetry ping still fires at session start, under your Mem0 account email,
unless `MEM0_TELEMETRY=false`):
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" pause
```
Confirm the new state back to the user, and remind them that already-created
memories still exist and remain searchable. Pending unsent packets are held
while paused, not expired, and are delivered after resuming. To turn capture
back on, use `/mem0:resume`.remember
When your agent uses it
Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
201 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore947 bytes
Read SKILL.md
# Remember something for future sessions
Mem0 creates memories from the session automatically — there is no separate
write command. When the user asks to remember something:
1. Restate the fact clearly and completely in your reply, in one or two
sentences, including any names, values, or paths it depends on. Your visible
reply is what memory extraction reads, so a precise restatement is what gets
remembered.
2. Tell the user it will be saved with this session's memories when the session
ends or compacts, and that it will surface in future sessions in this
repository (they can check later with /mem0:search).
Do not invent a storage confirmation or a memory ID — creation happens in theresume
When your agent uses it
Resume Mem0 memory capture after it was paused with /mem0:pause.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
98 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore434 bytesSKILL.mdcore434 bytes
Read SKILL.md
# Resume memory capture
Resume memory capture for this machine.
Run:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
create memories as normal; nothing that happened while paused is retroactively
captured.search
When your agent uses it
Search memories from earlier Coding Agent sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,204 bytes
Read SKILL.md
# Search memories
Call `search_memories` with the user's question. Treat `--top-k`, `--category`,
`--scope`, and `--run-id` as tool arguments instead of including them in the
query.
Omit `top_k` to use Mem0's configured default. Omit `category` to search every
category. Omit `scope` to use the configured default, normally `repo`: this
repository's shared memory, which everyone who works in it contributes to,
plus your own preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone.status
When your agent uses it
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
263 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,125 bytesSKILL.mdcore1,125 bytesSKILL.mdcore1,125 bytes
Read SKILL.md
# Memory status
Run both commands and report the combined result in plain language:
```bash
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" status --json
python3 "${PLUGIN_ROOT}/core/memory_cli.py" --harness "coding-agent" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is
active or paused, the user ID and repository scope (`repo_id`), whether an
API key is configured, the event/flush/retrieval counts (`flushes` is the
number of completed flushes, not a pending count), and the doctor check
results. If doctor reports an authentication failure (401 / invalid key), saymemory-triage
When your agent uses it
Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memory_add. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
4,783 tokensWhen the skill is activated
Reference documents
3,064 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Available Tools
- Decision Gate
- What to Extract (Priority Order)
- CRITICAL: Memory Completeness and Self-Containment
- How to Store
- What NEVER to Store
- Worked Examples
Files
SKILL.mdcore20,379 bytesSKILL.mdcore20,379 bytesdomains/companion.mddoc3,495 bytesrecall-protocol.mddoc10,169 bytes
Read SKILL.md
# Memory Protocol
You have persistent long-term memory powered by mem0. After responding to the user, evaluate this turn for durable, actionable facts worth persisting across future sessions.
Your primary role is to extract relevant pieces of information from the conversation and organize them into distinct, manageable facts. This allows for easy retrieval and personalization in future interactions.
**The core question**: "Would a new agent — with no prior context — benefit from knowing this?" If no → do nothing. Most turns produce zero memory operations. That is correct and expected.
## Available Tools
### memory_search
Semantic search across stored memories.
- `query` (required): search query
- `limit`: max results (default: configured topK)mem0-context-loader
When your agent uses it
Search memories from earlier OpenCode sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
364 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Constraints
- Output formatting
Files
SKILL.mdcore1,544 bytes
Read SKILL.md
# Context Loader
Pre-fetches relevant memories to prime context before working on a task.
## Steps
1. **Extract topics** from current message/task. Identify: file paths, module names, feature areas, error patterns.
2. **Call `search_memories` once** with a focused question about the task: `filters={"AND": [{"user_id": "<id>"}, {"app_id": "<pid>"}]}`, `top_k=10`.
3. **Output compact context block** (max 10 memories):
```
context-loader: loaded <N> memories for "<task summary>"mem0-forget
When your agent uses it
Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after experiments. Also handles undo of recent additions.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
691 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Undo recent writes
- Output formatting
Files
SKILL.mdcore2,658 bytes
Read SKILL.md
# Mem0 Forget
Delete specific memories from mem0.
## Execution
### Step 1: Parse input
The user provides either:
- A search query: `/mem0-forget auth module decisions`
- A memory ID: `/mem0-forget <memory_id>`
If no argument, ask: "What should I forget? Provide a search query or memory ID."
mem0-remember
When your agent uses it
Stores a memory verbatim from user input with appropriate type classification and metadata. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a decision, preference, convention, or learning.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
559 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Output formatting
Files
SKILL.mdcore2,241 bytes
Read SKILL.md
# Mem0 Remember
Store a fact or learning directly into mem0.
## Execution
### Step 1: Extract the content
The user provides the content as an argument: `/mem0-remember <text>`
If no text was provided, ask: "What should I remember?"
### Step 2: Classify the memory
mem0-scope
When your agent uses it
Views or changes the default memory scope (project, session, or global) used when saving and searching memories. Use when the user wants to control whether memories are scoped to this repo, this run, or shared across all their projects.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,146 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Output formatting
Files
SKILL.mdcore4,564 bytesSKILL.mdcore4,564 bytes
Read SKILL.md
# Mem0 Scope
View or change the **default memory scope** — the scope the memory tools use when
no explicit `scope` is given. The setting persists in `~/.mem0/settings.json`
(`default_scope`) and the plugin reads it fresh on each memory operation, so a
change takes effect immediately in the current session.
The three scopes:
- `project` (default) — this repo only. Filters by `user_id` + `app_id`.
- `session` — this run only. Adds `run_id` (the current session) so memories are
isolated to this conversation.
- `global` — across ALL your projects. Reads use `app_id="*"`; writes drop
`app_id` so the memory is user-wide.mem0-search
When your agent uses it
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
566 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Output formatting
Files
SKILL.mdcore2,012 bytes
Read SKILL.md
# Mem0 Search
Quick search with compact output. Lighter than `/mem0-tour`.
## Execution
### Step 1: Parse query
The user provides a search query: `/mem0-search auth middleware`
If no query provided, ask: "What should I search for?"
**Memory ID detection:** If the query matches any of these patterns, treat it as a
direct memory ID lookup instead of a search:mem0-status
When your agent uses it
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, add_memory errors occur, or to verify the plugin is working correctly.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
1,595 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Extended mode: Memory Quality Analysis
- Output formatting
Files
SKILL.mdcore6,088 bytesSKILL.mdcore6,088 bytesSKILL.mdcore6,088 bytesSKILL.mdcore6,088 bytesSKILL.mdcore6,088 bytes
Read SKILL.md
# Mem0 Status
Run a diagnostic check on the mem0 plugin. Useful for troubleshooting.
## Execution
Run ALL checks, then display a single summary. Do not stop on the first failure.
### Check 1: API key
```bash
[Credential-related source omitted]
[ -n "$_KEY" ] && echo "${_KEY:0:6}..." || echo "NOT_SET"
```mem0-tour
When your agent uses it
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
1,725 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Cross-project mode
- Peek mode (compact search)
- Execution
- Output formatting
Files
SKILL.mdcore6,574 bytes
Read SKILL.md
# Mem0 Project Tour
Show the user what mem0 has stored for the current project.
## Cross-project mode
When invoked with `--all-projects` (e.g., `/mem0-tour --all-projects` or
`/mem0-tour --all-projects auth middleware`), search across ALL projects:
1. Call `get_memories` with `filters={"AND": [{"user_id": "<active_user_id>"}]}`, `page_size=200` — **no `app_id` filter**.
2. If a search query was also provided, run `search_memories` with `query=<query>`,
`filters={"AND": [{"user_id": "<active_user_id>"}]}`, `top_k=20` — again no `app_id`.
3. Group results by `app_id` first, then by category within each project.
4. Display:context-loader
When your agent uses it
Search memories from earlier Pi sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
275 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Constraints
Files
SKILL.mdcore1,172 bytes
Read SKILL.md
# Context Loader
Pre-fetches relevant memories to prime context before working on a task or topic.
## Steps
1. **Extract topics** from current message/task. Identify: subject areas, people mentioned, project names, goal references.
2. **Call `mem0_memory` once** with `action="search"` and a focused question about the task.
3. **Output compact context block** (max 10 memories):
```
context-loader: loaded <N> memories for "<task summary>"forget
When your agent uses it
Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated information, incorrect memories, sensitive data, or cleaning up after experiments.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
384 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
Files
SKILL.mdcore1,440 bytes
Read SKILL.md
# Forget
Delete specific memories from Mem0.
## Execution
### Step 1: Parse input
The user provides either:
- A search query: `/mem0-forget travel plans`
- A memory ID: `/mem0-forget <memory_id>`
If no argument, ask: "What should I forget? Provide a search query or memory ID."
remember
When your agent uses it
Stores a memory verbatim from user input with appropriate category classification. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a preference, decision, goal, or lesson.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
433 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
Files
SKILL.mdcore1,641 bytes
Read SKILL.md
# Remember
Store a fact, preference, or learning directly into Mem0.
## Execution
### Step 1: Extract the content
The user provides the content as an argument: `/mem0-remember <text>`
If no text was provided, ask: "What should I remember?"
### Step 2: Classify the memory
search
When your agent uses it
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if something was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
347 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
Files
SKILL.mdcore1,207 bytes
Read SKILL.md
# Search / Peek
Quick semantic search with compact output. Lighter than `/mem0-tour`.
## Execution
### Step 1: Parse query
The user provides a search query: `/mem0-search favorite restaurants`
If no query provided, ask: "What should I search for?"
**Memory ID detection:** If the query matches a UUID pattern (`^[a-f0-9-]{20,}$`), treat it as a direct memory lookup instead of a search.
status
When your agent uses it
Diagnoses Mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, or to verify the plugin is working correctly.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
645 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Execution
- Extended mode: Memory Quality Analysis
Files
SKILL.mdcore2,616 bytes
Read SKILL.md
# Health Check / Status
Run a diagnostic check on the Mem0 plugin. Useful for troubleshooting.
## Execution
Run ALL checks, then display a single summary. Do not stop on the first failure.
### Check 1: API key
Verify the API key is configured. The plugin loads it from `MEM0_API_KEY` env var or `~/.pi/agent/mem0-config.json`.
- If not set: FAIL — "No API key configured"
- If set: PASS — show first 6 chars followed by `...`tour
When your agent uses it
Browses all stored memories grouped by category with full content display. Use when reviewing all memories, exploring stored knowledge, onboarding to a new session, or getting an overview of what the agent remembers.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
659 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Cross-project mode
- Search mode
- Execution
Files
SKILL.mdcore2,619 bytes
Read SKILL.md
# Memory Tour
Show the user what Mem0 has stored — a full walkthrough of all memories grouped by category.
## Cross-project mode
When invoked with `--all-projects` (e.g., `/mem0-tour --all-projects`), search across ALL projects:
1. Use `mem0_memory` tool with `action="get_all"`, `scope="global"` — no project filter.
2. Group results by project first, then by category within each project.
3. Display:
```
## <project_1> (<N> memories) <- current
**Goals** — <memory content>mem0
When your agent uses it
Mem0 Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (mem0ai), TypeScript SDK (mem0ai), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DEFAULT mem0 skill for ambiguous queries. DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell scripts (use mem0-cli), or Vercel AI SDK / @mem0/vercel-ai-provider / createMem0 (use mem0-vercel-ai-sdk).
What it loads into context
Frontmatter
367 tokensAlways available to the agent
SKILL.md
2,366 tokensWhen the skill is activated
Reference documents
37,613 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Install and authenticate
- Step 2: Initialize the client
- Step 3: Core operations
- Common integration pattern
- Common edge cases
- v2 Compatibility
- Live documentation search
- Client SDK References
- Platform References
- Related Mem0 Skills
Scripts executed separately
scripts/mem0_doc_search.py
Files
../mem0-cli/SKILL.mddoc8,039 bytes../mem0-vercel-ai-sdk/SKILL.mddoc9,178 bytesLICENSEasset10,705 bytesREADME.mddoc3,452 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesSKILL.mdcore8,801 bytesclient/differences.mddoc5,534 bytesclient/node.mddoc20,544 bytesclient/python.mddoc17,312 bytesreferences/api-reference.mddoc7,607 bytesreferences/architecture.mddoc12,488 bytesreferences/features.mddoc12,944 bytesreferences/integration-patterns.mddoc13,428 bytesreferences/quickstart.mddoc3,210 bytesreferences/sdk-guide.mddoc10,957 bytesreferences/use-cases.mddoc23,127 bytesscripts/mem0_doc_search.pyruns8,141 bytes
Read SKILL.md
# Mem0 Platform Integration
> **Skill Graph:** This skill is part of the Mem0 skill graph:
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript)
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider
Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.
## Step 1: Install and authenticate
**Python:**
```bash
pip install mem0aimem0-cli
When your agent uses it
Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0 config, mem0 import). Also triggers when query includes CLI flags like --user-id, --output, --json, --agent, or describes bash/zsh/terminal/shell usage. DO NOT TRIGGER when: user asks about programmatic SDK integration in Python/TS code (use mem0 skill), or Vercel AI SDK provider (use mem0-vercel-ai-sdk skill).
What it loads into context
Frontmatter
368 tokensAlways available to the agent
SKILL.md
2,192 tokensWhen the skill is activated
Reference documents
20,668 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- Setup
- Quick Reference
- Agent / JSON Mode
- Node and Python Differences
- Common Edge Cases
- References
- Related Mem0 Skills
Files
LICENSEasset10,705 bytesREADME.mddoc3,730 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesSKILL.mdcore8,039 bytesreferences/command-reference.mddoc32,499 bytesreferences/configuration.mddoc10,087 bytesreferences/workflows.mddoc10,882 bytes../mem0-vercel-ai-sdk/SKILL.mddoc9,178 bytes../mem0/SKILL.mddoc8,801 bytes
Read SKILL.md
# Mem0 CLI
The official command-line interface for the Mem0 memory platform. Add, search, list, update, and delete memories from the terminal -- for developers, AI agents, and CI/CD pipelines.
## Install
**Node.js (npm):**
```bash
npm install -g @mem0/cli
```
**Python (pip):**
```bash
pip install mem0-climem0-integrate
When your agent uses it
Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline. Detects the repo's language automatically and asks the user to pick between Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Writes failing tests before any implementation. Produces a local feature branch plus `.mem0-integration/` artifacts consumed by the paired verification skill. TRIGGER when: user says "integrate mem0", "add mem0 to this repo", "wire mem0 into <repo>", or asks how to add memory to an existing project. DO NOT TRIGGER when: the user wants general SDK usage (use skill:mem0), CLI usage (use skill:mem0-cli), or Vercel AI SDK (use skill:mem0-vercel-ai-sdk). After success, invoke skill:mem0-test-integration to verify in the same workspace (loose coupling).
What it loads into context
Frontmatter
304 tokensAlways available to the agent
SKILL.md
3,393 tokensWhen the skill is activated
Reference documents
5,920 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Canonical sources (fetch before deciding anything)
- Integration principles (non-negotiable)
- Skill delegation rules
- Preconditions
- Pipeline
- Artifacts (all under `.mem0-integration/`)
- Modes
- Invocation
- Exit codes
- Explicitly out of scope
Files
LICENSEasset10,705 bytesREADME.mddoc3,551 bytesSKILL.mdcore13,120 bytesSKILL.mdcore13,120 bytesreferences/pipeline.mddoc16,805 bytesreferences/subagent-prompts.mddoc3,077 bytes
Read SKILL.md
# mem0-integrate
Wire Mem0 into an existing repo with a goal-driven, test-first pipeline.
Pairs with `mem0-test-integration` for verification.
## Canonical sources (fetch before deciding anything)
The skill MUST `WebFetch` these URLs before step 3 and cite them in
`plan.md`. They are the ground truth — do not rely on ambient knowledge
of the Mem0 API.
### Agent-ready docs
- Scope-tagged docs index: https://docs.mem0.ai/llms.txt
- Full docs (single file, deep dives): https://docs.mem0.ai/llms-full.txtmem0-oss-to-platform
When your agent uses it
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local `Memory` class) to the mem0 Platform / hosted SDK (`MemoryClient`). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch from self-hosted mem0 to MemoryClient", "use my mem0 API key instead of a local Qdrant", "replace my local vector store + embedder config with the platform", even without the word "migrate". Covers Python (`Memory` to `MemoryClient`) and TypeScript (`mem0ai/oss` to `mem0ai`). Produces a reviewable plan, then executes it after approval. Touches only the mem0 integration. DO NOT TRIGGER when: adding mem0 to a project that has none (use `mem0-integrate`) or answering SDK usage questions (use `mem0`).
What it loads into context
Frontmatter
336 tokensAlways available to the agent
SKILL.md
2,242 tokensWhen the skill is activated
Reference documents
6,936 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The mental model (read this first — it's why the migration is shaped the way it is)
- Workflow
- Reference files
Files
LICENSEasset10,705 bytesREADME.mddoc3,222 bytesSKILL.mdcore8,763 bytesSKILL.mdcore8,763 bytesSKILL.mdcore8,763 bytesreferences/api-mapping.mddoc11,789 bytesreferences/gotchas.mddoc7,465 bytesreferences/plan-template.mddoc3,757 bytes
Read SKILL.md
# Migrate mem0 OSS → mem0 Platform (hosted)
This skill migrates a project's memory layer from the **self-hosted mem0 OSS SDK** to the
**hosted mem0 Platform SDK**, working for any project shape — an agent, a RAG pipeline, an API
service, a chatbot, a background worker. You discover where mem0 is actually used, write a plan the
developer reviews, and then execute it on approval.
## The mental model (read this first — it's why the migration is shaped the way it is)
OSS mem0 means **the developer runs the whole memory stack themselves**: a vector store
(Qdrant/pgvector/Chroma/…), an embedder, an LLM for fact extraction, and a local history DB. All of
that is wired up in a config object passed to `Memory`.
The Platform means **mem0 runs that stack for them**. The developer just holds an **API key**. Somem0-test-integration
When your agent uses it
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate and says "verify", "test the integration", "run /mem0-test-integration", or when a .mem0-integration/ directory exists and tests have not been run yet on the current branch. DO NOT TRIGGER when: the user wants to run general project tests (defer to the repo's native test command), or when no prior /mem0-integrate run exists in the current branch (ask them to run /mem0-integrate first). This skill ONLY catches compile and runtime bugs by design. Logical integration errors — wrong data stored, wrong time retrieved, wrong user scoping — are on the human reviewer.
What it loads into context
Frontmatter
336 tokensAlways available to the agent
SKILL.md
4,823 tokensWhen the skill is activated
Reference documents
870 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Canonical sources (use these, not ambient knowledge)
- Non-invasiveness contract
- Preconditions
- Pipeline
- Artifacts (all under `.mem0-integration/`)
- Modes
- Invocation
- Exit codes
- Explicitly out of scope
Files
LICENSEasset10,705 bytesREADME.mddoc3,349 bytesSKILL.mdcore18,321 bytesSKILL.mdcore18,321 bytesSKILL.mdcore18,321 bytesSKILL.mdcore18,321 bytes
Read SKILL.md
# mem0-test-integration
Verifies what `/mem0-integrate` produced. Runs in the same workspace,
on the same feature branch. Loose coupling — fast, catches compile and
runtime bugs, does not catch logical errors.
## Canonical sources (use these, not ambient knowledge)
All static checks and smoke-test shapes validate against these URLs.
`WebFetch` each before running step 3.
- Scope-tagged docs index: https://docs.mem0.ai/llms.txt
- OpenAPI (Platform REST): https://docs.mem0.ai/openapi.json
- Published SDK skill (canonical call patterns): https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0/SKILL.mdmem0-vercel-ai-sdk
When your agent uses it
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use mem0 skill), or CLI terminal commands (use mem0-cli skill).
What it loads into context
Frontmatter
321 tokensAlways available to the agent
SKILL.md
2,499 tokensWhen the skill is activated
Reference documents
13,777 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Install
- Step 2: Set up environment variables
- Pattern 1: Wrapped Model
- Pattern 2: Standalone Utilities
- Pattern 3: Streaming
- Supported Providers
- How It Works Internally
- Key Differences Between the 4 Utility Functions
- Common Edge Cases and Tips
- References
- Related Mem0 Skills
Files
../mem0-cli/SKILL.mddoc8,039 bytesLICENSEasset10,705 bytesREADME.mddoc3,241 bytesSKILL.mdcore9,178 bytesSKILL.mdcore9,178 bytesSKILL.mdcore9,178 bytesSKILL.mdcore9,178 bytesreferences/memory-utilities.mddoc11,394 bytesreferences/provider-api.mddoc10,230 bytesreferences/usage-patterns.mddoc10,671 bytes../mem0/SKILL.mddoc8,801 bytes
Read SKILL.md
# Mem0 Vercel AI SDK Provider
Memory-enhanced AI provider for Vercel AI SDK. Automatically retrieves and stores memories during LLM calls.
## Step 1: Install
```bash
npm install @mem0/vercel-ai-provider ai@^6
```
`ai` and the `@ai-sdk/*` provider packages ship as regular dependencies of `@mem0/vercel-ai-provider`, so nothing else needs installing. The only peer dependency is `zod` (optional, `^3.0.0`).
## Step 2: Set up environment variables
Skills included
- forget
- pause
- remember
- resume
- search
- status
- forget
- pause
- remember
- resume
- search
- status
- forget
- pause
- remember
- resume
- search
- status
- forget
- pause
- remember
- resume
- search
- status
- forget
- pause
- remember
- resume
- search
- status
- forget
- pause
- remember
- resume
- search
- status
- memory-triage
- mem0-context-loader
- mem0-forget
- mem0-remember
- mem0-scope
- mem0-search
- mem0-status
- mem0-tour
- context-loader
- forget
- remember
- search
- status
- tour
- mem0
- mem0-cli
- mem0-integrate
- mem0-oss-to-platform
- mem0-test-integration
- mem0-vercel-ai-sdk
Repository facts
- License
- Apache-2.0
- Created
- Jun 20, 2023
- Last pushed
- Nov 4, 2026
- Forks
- 8,131
- Open issues
- 455
- Project activity
- Active
Rank over the last 12 weeks
Now #27 · best #22 · down 2 in 30 days
- #23 from Sep 2 to Sep 11
- #24 from Sep 12 to Sep 16
- #25 from Sep 17 to Oct 18
- #26 from Oct 19 to Oct 24
- #29 on Oct 25
- #27 since Oct 28
2 earlier periods
- #21 on Aug 2
- #22 from Aug 7 to Sep 1
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 120 notes
integrations/antigravity-plugin/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/antigravity-plugin/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/antigravity-plugin/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/antigravity-plugin/skills/forget/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/codex-plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: memory-triage/SKILL.md:1
- 1 dangerous shell commandin 1 file: mem0-oss-to-platform/references/gotchas.md:14
- 340 network referencesin 38 files: skills/mem0-vercel-ai-sdk/SKILL.md:41 mem0/SKILL.md:27 mem0-integrate/SKILL.md:35 and 35 more
- No hidden or obfuscated text
- 3 instruction override signalsin 1 file: mem0-cli/references/command-reference.md:345
- 5 executable scriptsin 2 files: integrations/claude-code-plugin/core/memory_cli.py:1 mem0/scripts/mem0_doc_search.py:1
- 179 references to secretsin 42 files: skills/mem0-vercel-ai-sdk/SKILL.md:19 mem0/SKILL.md:22 mem0-cli/references/configuration.md:16 and 39 more
- No requests to vote in Hot
Show all 529 signals by file
integrations/antigravity-plugin/skills/status/SKILL.md
- Access to secretsline 23
[Credential-related source omitted]
integrations/claude-code-plugin/.claude-plugin/plugin.json
- Network accessline 6
"name": "Mem0" }, "homepage": "https://docs.mem0.ai/integrations/claude-code", - Network accessline 7
}, "homepage": "https://docs.mem0.ai/integrations/claude-code", "repository": "https://github.com/mem0ai/mem0", - Network accessline 8
"homepage": "https://docs.mem0.ai/integrations/claude-code", - Network accessline 9
"repository": "https://github.com/mem0ai/mem0", - Access to secretsline 13
[Credential-related source omitted]
integrations/claude-code-plugin/core/memory_cli.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted]
integrations/claude-code-plugin/skills/status/SKILL.md
- Access to secretsline 23
[Credential-related source omitted]
integrations/codex-plugin/skills/status/SKILL.md
- Access to secretsline 23
[Credential-related source omitted]
integrations/cursor-plugin/hooks/hooks.json
- Access to secretsline 4
[Credential-related source omitted]
integrations/cursor-plugin/skills/status/SKILL.md
- Access to secretsline 23
[Credential-related source omitted]
integrations/kimi-plugin/skills/status/SKILL.md
- Access to secretsline 23
[Credential-related source omitted]
integrations/mem0-agent-plugin/skills/status/SKILL.md
- Access to secretsline 22
[Credential-related source omitted]
integrations/openclaw/skills/memory-triage/SKILL.md
integrations/opencode-plugin/opencode-skills/mem0-status/SKILL.md
- Access to secretsline 17
[Credential-related source omitted]
integrations/pi-agent-plugin/skills/status/SKILL.md
- Access to secretsline 16
[Credential-related source omitted]
skills/mem0-cli/LICENSE
skills/mem0-cli/README.md
- Network accessline 3
Manage memories from the terminal using the [Mem0 CLI](https://docs.mem0.ai/platform/cli). This skill teaches Claude how to use every `mem0` command, flag, and output mode -- for both the Node.js and Python implementations. - Network accessline 19
npx skills add https://github.com/mem0ai/mem0 --skill mem0-cli - Network accessline 31
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Network accessline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Network accessline 34
-d '{"name": "mem0-cli", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli"}' - Network accessline 39
- A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli-readme)) - Access to secretsline 54
[Credential-related source omitted] - Network accessline 85
- [Mem0 Platform Dashboard](https://app.mem0.ai?utm_source=oss&utm_medium=skill-mem0-cli-readme) - Network accessline 86
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 87
- [Mem0 CLI Docs](https://docs.mem0.ai/platform/cli) - Network accessline 88
- [Mem0 GitHub](https://github.com/mem0ai/mem0) - Network accessline 94
| Skill | Purpose | Link | |-------|---------|------| | **mem0** | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 95
|-------|---------|------| | **mem0** | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | **mem0-cli** (this skill) | Terminal commands f - Network accessline 96
| **mem0** | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 97
| **mem0-cli** (this skill) | Terminal commands for memory operations | [local](./SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 98
| **mem0-vercel-ai-sdk** | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) |
skills/mem0-cli/SKILL.md
- Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Network accessline 68
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli - Network accessline 68
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli - Network accessline 68
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-cli - Network accessline 167
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 167
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 167
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 168
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-vercel-ai-sdk | Vercel AI SDK provider wit - Network accessline 168
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-vercel-ai-sdk | Vercel AI SDK provider wit - Network accessline 168
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-vercel-ai-sdk | Vercel AI SDK provider wit - Network accessline 169
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 169
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 169
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 170
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) | - Network accessline 170
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) | - Network accessline 170
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) |
skills/mem0-cli/references/command-reference.md
- Network accessline 20
| `-o, --output <format>` | string | Output format. Supported values vary per command (see matrix below). | | `--api-key <key>` | string | Override the API key for this invocation. Takes precedence over env var and config file. | | `--base- - Network accessline 22
| `--base-url <url>` | string | Override the API base URL (default: `https://api.mem0.ai`). | - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 106
[Credential-related source omitted] - Instruction override signalline 345
| `--project` | boolean | false | With `--all`: delete ALL memories project-wide (sends wildcard IDs). | | `--dry-run` | boolean | false | Show what would be deleted without actually deleting. Ignored by `--all --project`, which deletes (se - Instruction override signalline 346
| `--dry-run` | boolean | false | Show what would be deleted without actually deleting. Ignored by `--all --project`, which deletes (see Dry-run behavior). | | `--force` | boolean | false | Skip confirmation prompt (`--all` and `--entity` o - Instruction override signalline 347
| `--force` | boolean | false | Skip confirmation prompt (`--all` and `--entity` only). Required for those modes in `--json`/`--agent` mode. | - Access to secretsline 440
[Credential-related source omitted] - Access to secretsline 460
[Credential-related source omitted] - Access to secretsline 462
[Credential-related source omitted] - Access to secretsline 468
[Credential-related source omitted] - Network accessline 491
mem0 config set defaults.user_id alice mem0 config set platform.base_url https://api.mem0.ai - Network accessline 492
mem0 config set platform.base_url https://api.mem0.ai - Network accessline 625
"connected": true, "backend": "platform", "base_url": "https://api.mem0.ai" - Network accessline 626
"backend": "platform", "base_url": "https://api.mem0.ai" } - Network accessline 627
"base_url": "https://api.mem0.ai" - Access to secretsline 682
[Credential-related source omitted]
skills/mem0-cli/references/configuration.md
- Access to secretsline 16
[Credential-related source omitted] - Network accessline 31
[Credential-related source omitted] - Network accessline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Network accessline 33
"base_url": "https://api.mem0.ai", - Network accessline 58
| `defaults.run_id` | string | `""` | Default run ID for scoping commands. | | `platform.api_key` | string | `""` | API key for the Mem0 Platform. | | `platform.base_url` | string | `"https://api.mem0.ai"` | Base URL for API requests. | - Network accessline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Network accessline 60
| `platform.base_url` | string | `"https://api.mem0.ai"` | Base URL for API requests. | - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 145
[Credential-related source omitted] - Access to secretsline 154
[Credential-related source omitted] - Access to secretsline 157
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Network accessline 177
mem0 config set defaults.user_id alice mem0 config set platform.base_url https://api.mem0.ai - Network accessline 178
mem0 config set platform.base_url https://api.mem0.ai - Network accessline 193
|----------|-------------|------|---------| | `MEM0_API_KEY` | `platform.api_key` | string | `""` | | `MEM0_BASE_URL` | `platform.base_url` | string | `"https://api.mem0.ai"` | - Network accessline 194
[Credential-related source omitted] - Access to secretsline 194
[Credential-related source omitted] - Network accessline 195
| `MEM0_BASE_URL` | `platform.base_url` | string | `"https://api.mem0.ai"` | - Network accessline 210
[Credential-related source omitted] - Access to secretsline 210
[Credential-related source omitted] - Network accessline 212
4. Defaults Hardcoded defaults (empty strings, false, https://api.mem0.ai) - Access to secretsline 244
[Credential-related source omitted] - Access to secretsline 252
[Credential-related source omitted]
skills/mem0-cli/references/workflows.md
skills/mem0-integrate/LICENSE
skills/mem0-integrate/README.md
- Network accessline 3
Wire [Mem0](https://mem0.ai) into an existing repository end-to-end, using a goal-driven, test-first pipeline. - Network accessline 37
npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate - Network accessline 43
npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration - Network accessline 55
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Network accessline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Network accessline 58
-d '{"name": "mem0-integrate", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-integrate"}' - Network accessline 63
- A Mem0 Platform API key ([get one](https://app.mem0.ai/dashboard/api-keys)) *or* a working OSS setup (LLM + vector store) - Network accessline 82
- [Mem0 Platform Dashboard](https://app.mem0.ai) - Network accessline 83
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 84
- [Mem0 GitHub](https://github.com/mem0ai/mem0) - Network accessline 85
- [Platform vs OSS comparison](https://docs.mem0.ai/platform/platform-vs-oss)
skills/mem0-integrate/SKILL.md
- Network accessline 35
### Agent-ready docs - Scope-tagged docs index: https://docs.mem0.ai/llms.txt - Network accessline 36
- Scope-tagged docs index: https://docs.mem0.ai/llms.txt - Network accessline 37
- Full docs (single file, deep dives): https://docs.mem0.ai/llms-full.txt - Network accessline 38
- OpenAPI spec (Platform REST, machine-readable): https://docs.mem0.ai/openapi.json - Network accessline 39
- Hosted MCP server: https://mcp.mem0.ai/mcp (requires Platform API key) - Network accessline 40
- Integrations index: https://docs.mem0.ai/integrations - Network accessline 46
- SDK (Python + TS, Platform + OSS): https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0/SKILL.md - Network accessline 47
- CLI: https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0-cli/SKILL.md - Network accessline 48
- Vercel AI SDK: https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0-vercel-ai-sdk/SKILL.md - Network accessline 49
- Portable editor/MCP plugin: https://github.com/mem0ai/mem0/tree/main/integrations/mem0-agent-plugin - Network accessline 55
- Repo root: https://github.com/mem0ai/mem0 - Network accessline 56
- Python SDK: https://github.com/mem0ai/mem0/tree/main/mem0 - Network accessline 57
- TypeScript SDK: https://github.com/mem0ai/mem0/tree/main/mem0-ts - Network accessline 59
### Quickstarts (for bootstrapping unfamiliar stacks) - Platform: https://docs.mem0.ai/platform/quickstart - Network accessline 60
- Platform: https://docs.mem0.ai/platform/quickstart - Network accessline 61
- OSS Python: https://docs.mem0.ai/open-source/python-quickstart - Network accessline 62
- OSS Node: https://docs.mem0.ai/open-source/node-quickstart - Network accessline 63
- Platform vs OSS comparison: https://docs.mem0.ai/platform/platform-vs-oss - Network accessline 110
| `@ai-sdk/*` + `ai` in `package.json` | `skills/mem0-vercel-ai-sdk` | Integration is via `createMem0` provider wrapper, not raw `MemoryClient`. | | CLI-only repo (Typer, Commander, Click, Cobra) with no LLM call sites | `skills/mem0-cli` | - Network accessline 111
| CLI-only repo (Typer, Commander, Click, Cobra) with no LLM call sites | `skills/mem0-cli` | Call sites are command handlers, not model wrappers. Consider whether mem0 actually fits first. | | Target is an MCP client / editor config (Claud - Network accessline 112
| Target is an MCP client / editor config (Claude Code, Cursor, Codex settings) | `integrations/mem0-agent-plugin` | Local stdio MCP server (one search tool) plus skills, no hooks or automatic capture; for a hosted endpoint use `https://mcp - Access to secretsline 153
[Credential-related source omitted] - Access to secretsline 156
[Credential-related source omitted]
skills/mem0-integrate/references/pipeline.md
- Network accessline 87
Read the `## Identify the User's Setup` block in `https://docs.mem0.ai/llms.txt` for the Platform-first routing rules, then - Network accessline 88
`https://docs.mem0.ai/llms.txt` for the Platform-first routing rules, then - Network accessline 108
| Track | Key | Where to find | |---|---|---| | Platform | `MEM0_API_KEY` | https://app.mem0.ai | - Network accessline 109
|---|---|---| | Platform | `MEM0_API_KEY` | https://app.mem0.ai | | OSS (default LLM) | `OPENAI_API_KEY` | https://platform.openai.com/api-keys | - Network accessline 110
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Network accessline 111
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 120
[Credential-related source omitted] - Network accessline 281
- Platform method signatures: `https://docs.mem0.ai/openapi.json`, the request - Access to secretsline 297
[Credential-related source omitted] - Network accessline 309
- **Inputs**: the repo, `goal.md`, `plan.md`, the two test files, and direct URLs to the delegated skill (from `plan.md`), the SDK source (pinned per `mem0_tested_versions`), `https://docs.mem0.ai/llms.txt`, and - Network accessline 310
URLs to the delegated skill (from `plan.md`), the SDK source (pinned per `mem0_tested_versions`), `https://docs.mem0.ai/llms.txt`, and `https://docs.mem0.ai/openapi.json`. - Network accessline 311
`mem0_tested_versions`), `https://docs.mem0.ai/llms.txt`, and - Network accessline 312
`https://docs.mem0.ai/openapi.json`.
skills/mem0-integrate/references/subagent-prompts.md
- Network accessline 13
- the test files (do not change them either) - <delegated skill raw URL from plan.md> - https://docs.mem0.ai/llms.txt - Network accessline 14
- <delegated skill raw URL from plan.md> - https://docs.mem0.ai/llms.txt - https://docs.mem0.ai/openapi.json (Platform only) - Network accessline 15
- https://docs.mem0.ai/llms.txt - Network accessline 16
- https://docs.mem0.ai/openapi.json (Platform only)
skills/mem0-oss-to-platform/LICENSE
skills/mem0-oss-to-platform/README.md
- Network accessline 37
npx skills add https://github.com/mem0ai/mem0 --skill mem0-oss-to-platform - Network accessline 49
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Network accessline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Network accessline 52
-d '{"name": "mem0-oss-to-platform", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-oss-to-platform"}' - Network accessline 57
- A Mem0 Platform API key ([get one](https://app.mem0.ai/dashboard/api-keys)) - Network accessline 72
- [Mem0 Platform Dashboard](https://app.mem0.ai) - Network accessline 73
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 74
- [OSS → Platform migration guide](https://docs.mem0.ai/migration/oss-to-platform) - Network accessline 75
- [Platform vs OSS comparison](https://docs.mem0.ai/platform/platform-vs-oss)
skills/mem0-oss-to-platform/SKILL.md
- Access to secretsline 37
[Credential-related source omitted] - Network accessline 55
### Phase 0 — Prerequisite check The hosted SDK needs a mem0 API key (`MEM0_API_KEY`, obtainable at https://app.mem0.ai). Confirm - Network accessline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Network accessline 90
This verification step is the single most important habit — it's what keeps the plan correct across mem0 versions. Then consult `references/api-mapping.md` for the OSS→hosted translation of each method (Python and TypeScript). The docs guid - Network accessline 91
mem0 versions. Then consult `references/api-mapping.md` for the OSS→hosted translation of each method (Python and TypeScript). The docs guide is https://docs.mem0.ai/migration/oss-to-platform (verify its code samples against the installed S - Network accessline 92
method (Python and TypeScript). The docs guide is https://docs.mem0.ai/migration/oss-to-platform - Network accessline 94
https://docs.mem0.ai/migration/oss-v2-to-v3. - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 119
[Credential-related source omitted]
skills/mem0-oss-to-platform/references/api-mapping.md
- Network accessline 4
**Always confirm against the installed package** (see SKILL.md Phase 2), since versions drift. The facts below match Python `mem0ai` 2.2.x and TypeScript `mem0ai` 3.3.x (the `/v3/memories/*` platform API). Moving stored data: https://docs.m - Network accessline 5
facts below match Python `mem0ai` 2.2.x and TypeScript `mem0ai` 3.3.x (the `/v3/memories/*` platform API). Moving stored data: https://docs.mem0.ai/migration/oss-to-platform. OSS upgrade changes (Python 1.x to 2.x, TS 2.x to 3.x): https://d - Network accessline 6
API). Moving stored data: https://docs.mem0.ai/migration/oss-to-platform. OSS upgrade changes - Network accessline 7
(Python 1.x to 2.x, TS 2.x to 3.x): https://docs.mem0.ai/migration/oss-v2-to-v3 - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 147
[Credential-related source omitted]
skills/mem0-oss-to-platform/references/gotchas.md
- Network accessline 12
do, treat it as a separate, opt-in task: - **Hosted Qdrant + Python OSS SDK:** the repo ships `scripts/oss-to-platform-migrate.sh` (`curl -fsSL https://raw.githubusercontent.com/mem0ai/mem0/main/scripts/oss-to-platform-migrate.sh | bash`, - Network accessline 13
- **Hosted Qdrant + Python OSS SDK:** the repo ships `scripts/oss-to-platform-migrate.sh` (`curl -fsSL https://raw.githubusercontent.com/mem0ai/mem0/main/scripts/oss-to-platform-migrate.sh | bash`, documented at https://docs.mem0.ai/mig - Dangerous shell operationline 14
(`curl -fsSL https://raw.githubusercontent.com/mem0ai/mem0/main/scripts/oss-to-platform-migrate.sh | bash`, - Network accessline 14
(`curl -fsSL https://raw.githubusercontent.com/mem0ai/mem0/main/scripts/oss-to-platform-migrate.sh | bash`, - Network accessline 15
documented at https://docs.mem0.ai/migration/oss-to-platform). It needs `python3`, signs in to the - Network accessline 40
configure, and it only influences ranking (no separate `relations` payload, no typed relationships, no direct graph queries). Flag any project code that queried its own graph store or read `relations`. See https://docs.mem0.ai/platform/feat - Network accessline 42
See https://docs.mem0.ai/platform/features/graph-memory. - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted]
skills/mem0-oss-to-platform/references/plan-template.md
- Network accessline 15
## Prerequisites - `MEM0_API_KEY` must be set in the environment before execution/verification (https://app.mem0.ai). - Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted]
skills/mem0-test-integration/LICENSE
skills/mem0-test-integration/README.md
- Access to secretsline 18
[Credential-related source omitted] - Network accessline 36
npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration - Network accessline 42
npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate - Network accessline 54
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Network accessline 55
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Network accessline 57
-d '{"name": "mem0-test-integration", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-test-integration"}' - Network accessline 75
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 76
- [Mem0 GitHub](https://github.com/mem0ai/mem0) - Network accessline 77
- [API Reference](https://docs.mem0.ai/api-reference)
skills/mem0-test-integration/SKILL.md
- Network accessline 39
- Scope-tagged docs index: https://docs.mem0.ai/llms.txt - Network accessline 40
- OpenAPI (Platform REST): https://docs.mem0.ai/openapi.json - Network accessline 41
- Published SDK skill (canonical call patterns): https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0/SKILL.md - Network accessline 42
- Vercel AI SDK skill (if the target repo uses `@ai-sdk/*`): https://raw.githubusercontent.com/mem0ai/mem0/main/skills/mem0-vercel-ai-sdk/SKILL.md - Network accessline 43
- SDK source (cross-check version against frontmatter `mem0_tested_versions`): - Repo root: https://github.com/mem0ai/mem0 - Python: https://github.com/mem0ai/mem0/tree/main/mem0 - Network accessline 44
- Repo root: https://github.com/mem0ai/mem0 - Network accessline 45
- Python: https://github.com/mem0ai/mem0/tree/main/mem0 - Network accessline 46
- TypeScript: https://github.com/mem0ai/mem0/tree/main/mem0-ts - Access to secretsline 80
[Credential-related source omitted] - Network accessline 112
- **Import check**: does the write-site file import the expected Mem0 surface? Authoritative list comes from `## Identify the User's Setup` in `https://docs.mem0.ai/llms.txt`: - Network accessline 113
surface? Authoritative list comes from `## Identify the User's Setup` in `https://docs.mem0.ai/llms.txt`: - Platform Python → `from mem0 import MemoryClient` - Network accessline 114
in `https://docs.mem0.ai/llms.txt`: - Access to secretsline 178
[Credential-related source omitted] - Access to secretsline 194
[Credential-related source omitted] - Access to secretsline 199
[Credential-related source omitted]
skills/mem0-vercel-ai-sdk/LICENSE
skills/mem0-vercel-ai-sdk/README.md
- Network accessline 3
Add persistent memory to any Vercel AI SDK application using [@mem0/vercel-ai-provider](https://www.npmjs.com/package/@mem0/vercel-ai-provider). - Network accessline 19
npx skills add https://github.com/mem0ai/mem0 --skill mem0-vercel-ai-sdk - Network accessline 31
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Network accessline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Network accessline 34
-d '{"name": "mem0-vercel-ai-sdk", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk"}' - Network accessline 39
- **Node.js 18+** - **Vercel AI SDK v6** (`ai` package version 6.x) - A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk-readme)) - Network accessline 40
- **Vercel AI SDK v6** (`ai` package version 6.x) - A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk-readme)) - An LLM provider API key (OpenAI, Anthropic, Goo - Network accessline 41
- A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk-readme)) - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Network accessline 75
- [Mem0 Platform Dashboard](https://app.mem0.ai?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk-readme) - Network accessline 76
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 77
- [Mem0 GitHub](https://github.com/mem0ai/mem0) - Network accessline 78
- [@mem0/vercel-ai-provider on npm](https://www.npmjs.com/package/@mem0/vercel-ai-provider) - Network accessline 79
- [Vercel AI SDK Documentation](https://ai-sdk.dev/docs)
skills/mem0-vercel-ai-sdk/SKILL.md
- Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Network accessline 41
Get a Mem0 API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk - Network accessline 41
Get a Mem0 API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk - Network accessline 41
Get a Mem0 API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-vercel-ai-sdk - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Network accessline 193
- **Removed in 3.0.0**: `org_id`, `project_id`, `org_name`, `project_name`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version`. Graph memory is now a Mem0 Platform project setting, not a provider opti - Network accessline 193
- **Removed in 3.0.0**: `org_id`, `project_id`, `org_name`, `project_name`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version`. Graph memory is now a Mem0 Platform project setting, not a provider opti - Network accessline 193
- **Removed in 3.0.0**: `org_id`, `project_id`, `org_name`, `project_name`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version`. Graph memory is now a Mem0 Platform project setting, not a provider opti - Network accessline 195
- **Custom host**: set `host` in the config to point to a different Mem0 API endpoint (default: `https://api.mem0.ai`). - Network accessline 195
- **Custom host**: set `host` in the config to point to a different Mem0 API endpoint (default: `https://api.mem0.ai`). - Network accessline 195
- **Custom host**: set `host` in the config to point to a different Mem0 API endpoint (default: `https://api.mem0.ai`). - Network accessline 199
| Topic | File | |-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 199
| Topic | File | |-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 199
| Topic | File | |-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 200
|-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | | Memory utilities (`add - Network accessline 200
|-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | | Memory utilities (`add - Network accessline 200
|-------|------| | Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | | Memory utilities (`add - Network accessline 201
| Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 201
| Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 201
| Provider API (`createMem0`, `Mem0Provider`, types) | [local](references/provider-api.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/provider-api.md) | - Network accessline 202
| Memory utilities (`addMemories`, `retrieveMemories`, etc.) | [local](references/memory-utilities.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/memory-utilities.md) | - Network accessline 202
| Memory utilities (`addMemories`, `retrieveMemories`, etc.) | [local](references/memory-utilities.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/memory-utilities.md) | - Network accessline 202
| Memory utilities (`addMemories`, `retrieveMemories`, etc.) | [local](references/memory-utilities.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/memory-utilities.md) | - Network accessline 203
| Usage patterns and examples | [local](references/usage-patterns.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/usage-patterns.md) | - Network accessline 203
| Usage patterns and examples | [local](references/usage-patterns.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/usage-patterns.md) | - Network accessline 203
| Usage patterns and examples | [local](references/usage-patterns.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk/references/usage-patterns.md) | - Network accessline 207
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 207
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 207
| Skill | When to use | Link | |-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 208
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-cli | Terminal commands, scripting, CI/CD, - Network accessline 208
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-cli | Terminal commands, scripting, CI/CD, - Network accessline 208
|-------|-------------|------| | mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | | mem0-cli | Terminal commands, scripting, CI/CD, - Network accessline 209
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 209
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 209
| mem0 | Python/TypeScript SDK, REST API, framework integrations | [local](../mem0/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0) | - Network accessline 210
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 210
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 210
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) |
skills/mem0-vercel-ai-sdk/references/memory-utilities.md
- Access to secretsline 201
[Credential-related source omitted] - Network accessline 211
**Default host:** `https://api.mem0.ai` - Access to secretsline 261
[Credential-related source omitted] - Network accessline 263
| `threshold` | `number` | -- | Server-side relevance cutoff, not a floor on the returned score; sent only when set | | `rerank` | `boolean` | -- (API default `false`) | Enable re-ranking, sent only when set | | `host` | `string` | `https:/ - Network accessline 265
| `host` | `string` | `https://api.mem0.ai` | Custom API host |
skills/mem0-vercel-ai-sdk/references/provider-api.md
- Network accessline 54
interface Mem0ProviderSettings { baseURL?: string; // Stored on the model config (default: "https://api.openai.com"), not applied to upstream LLM requests - Network accessline 55
baseURL?: string; // Stored on the model config (default: "https://api.openai.com"), not applied to upstream LLM requests - Access to secretsline 58
[Credential-related source omitted] - Network accessline 76
| `mem0Config` | Default Mem0 settings for all calls | `{ user_id: "alice" }` | | `config` | Provider-specific SDK settings | `{ organization: "org-xxx" }` for OpenAI | | `config.baseURL` | Override LLM provider base URL (put it inside `con - Network accessline 78
| `config.baseURL` | Override LLM provider base URL (put it inside `config`; the top-level `baseURL` does not reach the upstream client) | `{ baseURL: "https://my-proxy.example.com/v1" }` | - Network accessline 112
threshold?: number; // Server-side relevance cutoff; sent only when set rerank?: boolean; // Enable re-ranking of search results; sent only when set (API default: false) host?: string; // Custom M - Network accessline 113
rerank?: boolean; // Enable re-ranking of search results; sent only when set (API default: false) host?: string; // Custom Mem0 API host (default: "https://api.mem0.ai") } - Network accessline 114
host?: string; // Custom Mem0 API host (default: "https://api.mem0.ai") - Network accessline 188
[Credential-related source omitted] - Access to secretsline 188
[Credential-related source omitted]
skills/mem0-vercel-ai-sdk/references/usage-patterns.md
- Access to secretsline 3
[Credential-related source omitted] - Network accessline 301
const mem0 = createMem0({ mem0Config: { host: "https://my-mem0-instance.example.com", - Network accessline 302
mem0Config: { host: "https://my-mem0-instance.example.com", }, - Network accessline 303
host: "https://my-mem0-instance.example.com", - Network accessline 311
const memories = await retrieveMemories(prompt, { user_id: "alice", host: "https://my-mem0-instance.example.com", - Network accessline 312
user_id: "alice", host: "https://my-mem0-instance.example.com", }); - Network accessline 313
host: "https://my-mem0-instance.example.com",
skills/mem0/LICENSE
skills/mem0/README.md
- Network accessline 3
Add persistent memory to any AI application in minutes using [Mem0 Platform](https://app.mem0.ai?utm_source=oss&utm_medium=skill-mem0-readme) or the open-source self-hosted SDK. - Network accessline 21
npx skills add https://github.com/mem0ai/mem0 --skill mem0 - Network accessline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Network accessline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Network accessline 36
-d '{"name": "mem0", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0"}' - Network accessline 41
- A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-readme)) - Access to secretsline 46
[Credential-related source omitted] - Network accessline 84
- [Mem0 Platform Dashboard](https://app.mem0.ai?utm_source=oss&utm_medium=skill-mem0-readme) - Network accessline 85
- [Mem0 Documentation](https://docs.mem0.ai) - Network accessline 86
- [Mem0 GitHub](https://github.com/mem0ai/mem0) - Network accessline 87
- [API Reference](https://docs.mem0.ai/api-reference)
skills/mem0/SKILL.md
- Access to secretsline 22
[Credential-related source omitted] - Access to secretsline 22
[Credential-related source omitted] - Access to secretsline 22
[Credential-related source omitted] - Network accessline 27
> **Skill Graph:** This skill is part of the Mem0 skill graph: > - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/m - Network accessline 27
> **Skill Graph:** This skill is part of the Mem0 skill graph: > - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/m - Network accessline 27
> **Skill Graph:** This skill is part of the Mem0 skill graph: > - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/m - Network accessline 28
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface > - **[mem0-vercel-ai-sdk]( - Network accessline 28
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface > - **[mem0-vercel-ai-sdk]( - Network accessline 28
> - **mem0** (this skill) -- Platform Client SDK + OSS (Python + TypeScript) > - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface > - **[mem0-vercel-ai-sdk]( - Network accessline 29
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface - Network accessline 29
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface - Network accessline 29
> - **[mem0-cli](../mem0-cli/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli)) -- Command-line interface - Network accessline 30
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider - Network accessline 30
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider - Network accessline 30
> - **[mem0-vercel-ai-sdk](../mem0-vercel-ai-sdk/SKILL.md)** ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)) -- Vercel AI SDK provider - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 48
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0 - Network accessline 48
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0 - Network accessline 48
Get an API key at: https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0 - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 57
[Credential-related source omitted] - Access to secretsline 57
[Credential-related source omitted] - Access to secretsline 57
[Credential-related source omitted] - Network accessline 151
See the [Platform migration guide](https://docs.mem0.ai/migration/platform-v2-to-v3) and the [OSS migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details. - Network accessline 151
See the [Platform migration guide](https://docs.mem0.ai/migration/platform-v2-to-v3) and the [OSS migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details. - Network accessline 151
See the [Platform migration guide](https://docs.mem0.ai/migration/platform-v2-to-v3) and the [OSS migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details. - Network accessline 191
| Skill | When to use | Link | |-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 191
| Skill | When to use | Link | |-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 191
| Skill | When to use | Link | |-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 192
|-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | | mem0-vercel-ai-sdk | Vercel AI SDK pr - Network accessline 192
|-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | | mem0-vercel-ai-sdk | Vercel AI SDK pr - Network accessline 192
|-------|-------------|------| | mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | | mem0-vercel-ai-sdk | Vercel AI SDK pr - Network accessline 193
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 193
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 193
| mem0-cli | Terminal commands, scripting, CI/CD, agent tool loops | [local](../mem0-cli/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-cli) | - Network accessline 194
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) | - Network accessline 194
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) | - Network accessline 194
| mem0-vercel-ai-sdk | Vercel AI SDK provider with automatic memory | [local](../mem0-vercel-ai-sdk/SKILL.md) / [GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk) |
skills/mem0/client/differences.md
skills/mem0/client/node.md
- Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 27
- HTTP library: native `fetch` (the axios instance in `mem0.ts` is unused) - Timeout: none set by the SDK - Base URL: `https://api.mem0.ai` (override with `host`) - Network accessline 28
- Timeout: none set by the SDK - Base URL: `https://api.mem0.ai` (override with `host`) - All methods are async (return `Promise`) - Network accessline 29
- Base URL: `https://api.mem0.ai` (override with `host`) - Network accessline 238
// Create (always uses the project resolved from your API key) const webhook = await client.createWebhook({ url: 'https://your-app.com/webhook', - Network accessline 239
const webhook = await client.createWebhook({ url: 'https://your-app.com/webhook', name: 'Memory Logger', - Network accessline 240
url: 'https://your-app.com/webhook', - Network accessline 247
webhookId: 'wh_123', name: 'Updated Logger', url: 'https://new-url.com', - Network accessline 248
name: 'Updated Logger', url: 'https://new-url.com', }); - Network accessline 249
url: 'https://new-url.com', - Network accessline 507
See the [v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details.
skills/mem0/client/python.md
- Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 21
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 26
- HTTP library: `httpx` - Timeout: 300 seconds - Base URL: `https://api.mem0.ai` - Network accessline 28
- Base URL: `https://api.mem0.ai` - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Network accessline 300
# Create webhook = client.create_webhook( url="https://your-app.com/webhook", - Network accessline 301
webhook = client.create_webhook( url="https://your-app.com/webhook", name="Memory Logger", - Network accessline 302
url="https://your-app.com/webhook", - Network accessline 308
# Update client.update_webhook(webhook_id="wh_123", name="Updated", url="https://new-url.com") - Network accessline 309
client.update_webhook(webhook_id="wh_123", name="Updated", url="https://new-url.com") - Access to secretsline 365
[Credential-related source omitted] - Access to secretsline 377
[Credential-related source omitted] - Access to secretsline 384
[Credential-related source omitted] - Access to secretsline 474
[Credential-related source omitted] - Network accessline 522
See the [v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for full details.
skills/mem0/references/api-reference.md
- Network accessline 3
REST API endpoints for the Mem0 Platform. Base URL: `https://api.mem0.ai` - Access to secretsline 5
[Credential-related source omitted] - Network accessline 155
{ "count": 123, "next": "https://api.mem0.ai/v3/memories/?page=2&page_size=50", - Network accessline 156
"count": 123, "next": "https://api.mem0.ai/v3/memories/?page=2&page_size=50", "previous": null, - Network accessline 157
"next": "https://api.mem0.ai/v3/memories/?page=2&page_size=50",
skills/mem0/references/features.md
- Network accessline 72
See the [v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details. - Network accessline 308
npx mcp-add --name mem0-mcp --type http --url "https://mcp.mem0.ai/mcp" - Network accessline 309
--name mem0-mcp \ --type http \ --url "https://mcp.mem0.ai/mcp" \ - Network accessline 310
--type http \ --url "https://mcp.mem0.ai/mcp" \ --clients "claude code,cursor,windsurf,vscode,opencode" - Network accessline 311
--url "https://mcp.mem0.ai/mcp" \ - Network accessline 358
webhook = client.create_webhook( url="https://your-app.com/webhook", - Network accessline 359
url="https://your-app.com/webhook", - Network accessline 369
const webhook = await client.createWebhook({ url: 'https://your-app.com/webhook', - Network accessline 370
url: 'https://your-app.com/webhook', - Network accessline 385
client.update_webhook( name="Updated Logger", url="https://your-app.com/new-webhook", - Network accessline 386
name="Updated Logger", url="https://your-app.com/new-webhook", event_types=["memory_update", "memory_add"], - Network accessline 387
url="https://your-app.com/new-webhook",
skills/mem0/references/integration-patterns.md
- Network accessline 22
Source: [docs.mem0.ai/integrations/langchain](https://docs.mem0.ai/integrations/langchain) - Network accessline 67
Source: [docs.mem0.ai/integrations/crewai](https://docs.mem0.ai/integrations/crewai) - Network accessline 71
Newer CrewAI versions removed the `memory_config={"provider": "mem0"}` shortcut on `Crew(...)`. Wire Mem0 in explicitly through `MemoryClient` (retrieve, inject into the task, store). CrewAI's own `ExternalMemory` API is the native alternat - Network accessline 120
> **Dedicated skill available.** For comprehensive Vercel AI SDK documentation, see the [mem0-vercel-ai-sdk skill](../../mem0-vercel-ai-sdk/SKILL.md) ([GitHub](https://github.com/mem0ai/mem0/tree/main/skills/mem0-vercel-ai-sdk)). - Network accessline 143
Source: [docs.mem0.ai/integrations/openai-agents-sdk](https://docs.mem0.ai/integrations/openai-agents-sdk) - Network accessline 211
Source: [docs.mem0.ai/integrations/pipecat](https://docs.mem0.ai/integrations/pipecat) - Access to secretsline 221
[Credential-related source omitted] - Network accessline 248
Source: [docs.mem0.ai/integrations/langgraph](https://docs.mem0.ai/integrations/langgraph) - Network accessline 306
Source: [docs.mem0.ai/integrations/llama-index](https://docs.mem0.ai/integrations/llama-index) - Network accessline 343
Source: [docs.mem0.ai/integrations/autogen](https://docs.mem0.ai/integrations/autogen) - Access to secretsline 360
[Credential-related source omitted] - Network accessline 390
| Framework | Type | Install | |-----------|------|---------| | [Mastra](https://docs.mem0.ai/integrations/mastra) | TS agent framework | `npm install @mastra/core @mastra/mem0 @ai-sdk/openai zod` | - Network accessline 391
|-----------|------|---------| | [Mastra](https://docs.mem0.ai/integrations/mastra) | TS agent framework | `npm install @mastra/core @mastra/mem0 @ai-sdk/openai zod` | | [ElevenLabs](https://docs.mem0.ai/integrations/elevenlabs) | Voice AI - Network accessline 392
| [Mastra](https://docs.mem0.ai/integrations/mastra) | TS agent framework | `npm install @mastra/core @mastra/mem0 @ai-sdk/openai zod` | - Network accessline 393
| [ElevenLabs](https://docs.mem0.ai/integrations/elevenlabs) | Voice AI | `pip install elevenlabs mem0ai` | - Network accessline 394
| [LiveKit](https://docs.mem0.ai/integrations/livekit) | Real-time voice/video | `pip install livekit-agents mem0ai` | - Network accessline 395
| [Camel AI](https://docs.mem0.ai/integrations/camel-ai) | Multi-agent framework | `pip install "camel-ai>=0.2.0" mem0ai` | - Network accessline 396
| [AWS Bedrock](https://docs.mem0.ai/integrations/aws-bedrock) | Cloud LLM provider | `pip install mem0ai boto3 opensearch-py` | - Network accessline 397
| [Dify](https://docs.mem0.ai/integrations/dify) | Low-code AI platform | Plugin-based | - Network accessline 398
| [Google AI ADK](https://docs.mem0.ai/integrations/google-ai-adk) | Google agent framework | `pip install google-adk mem0ai` | - Network accessline 399
| [Agno](https://docs.mem0.ai/integrations/agno) | Multimodal agent framework | `pip install agno mem0ai` | - Network accessline 400
| [Strands Agents](https://docs.mem0.ai/integrations/strands) | AWS agent SDK (native `MemoryStore`) | `pip install mem0-strands` | - Network accessline 401
| [LangChain Tools](https://docs.mem0.ai/integrations/langchain-tools) | Mem0 tools for any LangChain agent | `pip install langchain_core mem0ai` |
skills/mem0/references/quickstart.md
- Network accessline 7
- Python 3.10+ or Node.js 18+ - A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-quickstart)) - Network accessline 8
- A Mem0 Platform API key ([Get one here](https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=skill-mem0-quickstart)) - Access to secretsline 14
[Credential-related source omitted] - Access to secretsline 20
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Network accessline 76
# Add memory curl -X POST https://api.mem0.ai/v3/memories/add/ \ - Network accessline 77
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Network accessline 88
# Search memories curl -X POST https://api.mem0.ai/v3/memories/search/ \ - Network accessline 89
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted]
skills/mem0/references/sdk-guide.md
skills/mem0/references/use-cases.md
- Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 171
[Credential-related source omitted] - Access to secretsline 261
[Credential-related source omitted] - Access to secretsline 356
[Credential-related source omitted] - Access to secretsline 461
[Credential-related source omitted] - Network accessline 491
- Query at any scope level — user, agent, session, or app-wide - No memory leakage between tenants - When `add` gets both `user_id` and `agent_id`, each fact is attributed to its speaker (user messages carry `user_id`, assistant messages ca - Network accessline 493
- When `add` gets both `user_id` and `agent_id`, each fact is attributed to its speaker (user messages carry `user_id`, assistant messages carry `agent_id`), so an `AND` of both ids returns nothing; use `OR` (see [entity-scoped memory](http - Access to secretsline 551
[Credential-related source omitted] - Access to secretsline 630
[Credential-related source omitted] - Network accessline 721
For 30+ cookbooks with complete working code: [docs.mem0.ai/cookbooks/overview](https://docs.mem0.ai/cookbooks/overview)
skills/mem0/scripts/mem0_doc_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 33
DOCS_BASE = "https://docs.mem0.ai" DOCS_HOST = urllib.parse.urlsplit(DOCS_BASE).netloc - Network accessline 66
require_docs_url(url) opener = urllib.request.build_opener(DocsRedirectHandler) req = urllib.request.Request(url, headers={"User-Agent": "Mem0DocSearchAgent/1.0"}) - Network accessline 67
opener = urllib.request.build_opener(DocsRedirectHandler) req = urllib.request.Request(url, headers={"User-Agent": "Mem0DocSearchAgent/1.0"}) try: - Network accessline 68
req = urllib.request.Request(url, headers={"User-Agent": "Mem0DocSearchAgent/1.0"})
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 500 facts
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:23Low confidence
- Executable script in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:1High confidence
- Executable script in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:1High confidence
- Executable script in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:1High confidence
- Executable script in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:1High confidence
- Access to secrets in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:13High confidence
- Access to secrets in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:13High confidence
- Access to secrets in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:13High confidence
- Access to secrets in code of a file that runsintegrations/claude-code-plugin/core/memory_cli.py:13High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:87Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:87Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:87Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:87Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:101Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:101Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:101Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueintegrations/claude-code-plugin/core/memory_cli.py:101Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:23Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:23Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:23Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:23Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:22Low confidence
- Broad permissions in the frontmatter of the SKILL.mdmemory-triage/SKILL.md:1High confidence
- Access to secrets in the frontmatter of the SKILL.mdmemory-triage/SKILL.md:10Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuemem0-status/SKILL.md:17Low confidence
- Access to secrets in prose of the SKILL.mdstatus/SKILL.md:16Low confidence
- Network access in prose of documentationmem0-cli/README.md:3Low confidence
- Network access in code of documentationmem0-cli/README.md:19Low confidence
- Network access in code of documentationmem0-cli/README.md:31Low confidence
- Access to secrets in code of documentationmem0-cli/README.md:31Low confidence
- Network access in code of documentationmem0-cli/README.md:32Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuemem0-cli/README.md:32Low confidence
- Network access in code of documentationmem0-cli/README.md:34Low confidence
- Network access in prose of documentationmem0-cli/README.md:39Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuemem0-cli/README.md:54Low confidence
- Network access in prose of documentationmem0-cli/README.md:85Low confidence
- Network access in prose of documentationmem0-cli/README.md:86Low confidence
- Network access in prose of documentationmem0-cli/README.md:87Low confidence
- Network access in prose of documentationmem0-cli/README.md:88Low confidence
- Network access in prose of documentationmem0-cli/README.md:94Low confidence
- Network access in prose of documentationmem0-cli/README.md:95Low confidence
- Network access in prose of documentationmem0-cli/README.md:96Low confidence
- Network access in prose of documentationmem0-cli/README.md:97Low confidence
- Network access in prose of documentationmem0-cli/README.md:98Low confidence
- Access to secrets in the frontmatter of the SKILL.mdskills/mem0-cli/SKILL.md:19Low confidence
- Access to secrets in the frontmatter of the SKILL.mdmem0-cli/SKILL.md:19Low confidence
- Access to secrets in the frontmatter of the SKILL.mdskills/mem0-cli/SKILL.md:19Low confidence
- Access to secrets in code of the SKILL.mdskills/mem0-cli/SKILL.md:65High confidence
- Access to secrets in code of the SKILL.mdmem0-cli/SKILL.md:65High confidence
- Access to secrets in code of the SKILL.mdskills/mem0-cli/SKILL.md:65High confidence
and 450 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest .github/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md integrations/antigravity-plugin/skills/forget/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md integrations/antigravity-plugin/skills/forget/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md integrations/antigravity-plugin/skills/forget/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md integrations/antigravity-plugin/skills/forget/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/mem0ai-mem0/)