Alternatives to mims-harvard/ToolUniverse
Explore 3 related skill repositories alongside mims-harvard/ToolUniverse.
View mims-harvard/ToolUniverseRelated repositories are selected from shared categories, topics and mentions in the same lists. Order follows the export’s relevance signals. These links are independent of sponsorship and do not change the leaderboard.
DenisSergeevitch/agents-best-practices
Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interact
- GitHub stars
- 2,422
- Star growth over 7 days
- +0.6%
- Heat
- 6.0
- Before you install
- Local scripts
- Median activation tokens (estimate)
- 6,520 tokens
- Project activity
- Active
- License
- MIT
- Supported agents
- Not available
RyanAlberts/best-of-Agent-Harnesses
🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
- GitHub stars
- 1,467
- Star growth over 7 days
- +3.2%
- Heat
- 7.7
- Before you install
- Network or broad shell
- Median activation tokens (estimate)
- 3,119.5 tokens
- Project activity
- Active
- License
- CC-BY-SA-4.0
- Supported agents
- Claude Code, Codex, Cursor
BuilderIO/agent-native
A framework for building agentic apps
- GitHub stars
- 7,635
- Star growth over 7 days
- +0.9%
- Heat
- 6.9
- Before you install
- Network or broad shell
- Median activation tokens (estimate)
- Not available
- Project activity
- Active
- License
- MIT
- Supported agents
- Claude Code, Codex, Gemini CLI
Token cost is the median frontmatter plus SKILL.md estimate per skill. Reference files load on demand and scripts run separately. The estimate is unavailable when skill records or token counts are incomplete. Missing growth or heat history stays unmeasured, never zero.
Automated signals, not a guarantee Methodology
