Not in the top 1,000 by GitHub stars
JasmyLab-JANCTION/janction-render
Cloud GPU rendering for Blender scenes and 3D models (GLB/FBX/USD/STL) for AI agents: MCP server, HTTP API, CLI. Product shots, turntables, animations from Claude, ChatGPT, Codex, Cursor. Free to start (100 JPY with no card, 400 JPY more after saving a card), then 0.1 JPY per GPU-second.
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
plugins/janction-render/skills/janction-render/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8f4bdc53d9a3
No earlier version was observed for comparison.
skills/janction-render/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8f4bdc53d9a3
No earlier version was observed for comparison.
Verified commit 8f4bdc53d9a34e328fc51149d33366e0573d31e4
git clone --filter=blob:none --no-checkout https://github.com/JasmyLab-JANCTION/janction-render.git .hotskills/jasmylab-janction-janction-render && git -C .hotskills/jasmylab-janction-janction-render checkout --detach 8f4bdc53d9a34e328fc51149d33366e0573d31e4
# Copy each selected skill directory from .hotskills/jasmylab-janction-janction-render into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/JasmyLab-JANCTION/janction-render.git .hotskills/jasmylab-janction-janction-render && git -C .hotskills/jasmylab-janction-janction-render checkout --detach 8f4bdc53d9a34e328fc51149d33366e0573d31e4
# Copy each selected skill directory from .hotskills/jasmylab-janction-janction-render into .gemini/skills/<skill-name>/Heat
4.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- janction-render
plugins/janction-render/skills/janction-render - janction-render
skills/janction-render
How it works
janction-render
When your agent uses it
Render Blender scenes, bpy scripts, 3D files (GLB, glTF, FBX, USD, OBJ) and animations on remote NVIDIA GPUs through the JANCTION Render MCP server, with no local Blender or GPU. Use when the user wants a rendered image or video of 3D content - preview a Blender scene, render a bpy script, turn a GLB/FBX/USD model into product shots or a 360-degree turntable MP4, render a Blender animation to MP4, or render on a machine without an NVIDIA GPU or where Cycles is slow. Flow - preview, fix, estimate the cost, ask, render, download.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
2,681 tokensWhen the skill is activated
Reference documents
1,515 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it connected?
- Standard flow
- Rules
- When something fails
- Writing a scene script
Files
../../../../.claude-plugin/marketplace.jsonasset670 bytes../../.claude-plugin/plugin.jsonasset728 bytesSKILL.mdcore10,599 bytesSKILL.mdcore10,599 bytesreferences/examples.mddoc2,364 bytesreferences/troubleshooting.mddoc3,503 bytes
Read SKILL.md
# JANCTION Render
<!-- terms:skill_terms_en -->
The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's
NVIDIA GPUs. A new key gets 100 JPY of free GPU time (14 days; one per network every 30 days, further keys on the same
network share what is left), and 400 JPY more, once per card, when the user saves a card on a Stripe page that charges
nothing (the service offers it as `card_offer` once the 100 JPY is used up; tell the user it costs nothing). When a reply
carries `autocharge_offer` (the credit is about to run out), ask the user once whether to turn on auto top-up and share its
link only if they say yes; after that, previews are free up to 2 GPU-minutes a day and other renders cost 0.1 JPY per
GPU-second from prepaid credit (top-ups from 100 JPY). Up to 3,000 frames per instruction (run as parts of 240 under one job id):
1920x1080 on free time, up to 3840x2160 on prepaid credit. Inputs and results are deleted 24 hours after last use
(7 days, normally, for keys that have paid 500 JPY or more in total). Every estimate carries `decision` (`can_execute`,
`blocking_reasons`, `required_actions`): when it says the job cannot run, say so and offer the listed actions; do not promise
that a top-up alone makes it run.View the complete source on GitHubjanction-render
When your agent uses it
Render Blender scenes, bpy scripts, 3D files (GLB, glTF, FBX, USD, OBJ) and animations on remote NVIDIA GPUs through the JANCTION Render MCP server, with no local Blender or GPU. Use when the user wants a rendered image or video of 3D content - preview a Blender scene, render a bpy script, turn a GLB/FBX/USD model into product shots or a 360-degree turntable MP4, render a Blender animation to MP4, or render on a machine without an NVIDIA GPU or where Cycles is slow. Flow - preview, fix, estimate the cost, ask, render, download.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
2,681 tokensWhen the skill is activated
Reference documents
1,515 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Is it connected?
- Standard flow
- Rules
- When something fails
- Writing a scene script
Files
SKILL.mdcore10,599 bytesSKILL.mdcore10,599 bytesreferences/examples.mddoc2,364 bytesreferences/troubleshooting.mddoc3,503 bytes
Read SKILL.md
# JANCTION Render
<!-- terms:skill_terms_en -->
The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's
NVIDIA GPUs. A new key gets 100 JPY of free GPU time (14 days; one per network every 30 days, further keys on the same
network share what is left), and 400 JPY more, once per card, when the user saves a card on a Stripe page that charges
nothing (the service offers it as `card_offer` once the 100 JPY is used up; tell the user it costs nothing). When a reply
carries `autocharge_offer` (the credit is about to run out), ask the user once whether to turn on auto top-up and share its
link only if they say yes; after that, previews are free up to 2 GPU-minutes a day and other renders cost 0.1 JPY per
GPU-second from prepaid credit (top-ups from 100 JPY). Up to 3,000 frames per instruction (run as parts of 240 under one job id):
1920x1080 on free time, up to 3840x2160 on prepaid credit. Inputs and results are deleted 24 hours after last use
(7 days, normally, for keys that have paid 500 JPY or more in total). Every estimate carries `decision` (`can_execute`,
`blocking_reasons`, `required_actions`): when it says the job cannot run, say so and offer the listed actions; do not promise
that a top-up alone makes it run.View the complete source on GitHubSkills included
- janction-render
- janction-render
Repository facts
- License
- MIT
- Created
- Sep 30, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
plugins/janction-render/skills/janction-render/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/janction-render/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 20 network referencesin 6 files: .claude-plugin/marketplace.json:4 plugins/janction-render/.claude-plugin/plugin.json:6 janction-render/SKILL.md:8 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 20 signals by file
.claude-plugin/marketplace.json
- Network accessline 4
"owner": { "name": "JasmyLab Inc.", "url": "https://render.janction.jp" - Network accessline 5
"name": "JasmyLab Inc.", "url": "https://render.janction.jp" }, - Network accessline 6
"url": "https://render.janction.jp" - Network accessline 13
"category": "productivity", "tags": ["blender", "rendering", "gpu", "3d", "mcp"], "homepage": "https://render.janction.jp", - Network accessline 14
"tags": ["blender", "rendering", "gpu", "3d", "mcp"], "homepage": "https://render.janction.jp", "license": "MIT" - Network accessline 15
"homepage": "https://render.janction.jp",
plugins/janction-render/.claude-plugin/plugin.json
- Network accessline 6
"author": { "name": "JasmyLab Inc.", "url": "https://render.janction.jp" - Network accessline 7
"name": "JasmyLab Inc.", "url": "https://render.janction.jp" }, - Network accessline 8
"url": "https://render.janction.jp" - Network accessline 9
}, "homepage": "https://render.janction.jp", "repository": "https://github.com/JasmyLab-JANCTION/janction-render", - Network accessline 10
"homepage": "https://render.janction.jp", - Network accessline 11
"repository": "https://github.com/JasmyLab-JANCTION/janction-render",
plugins/janction-render/skills/janction-render/SKILL.md
- Network accessline 8
<!-- terms:skill_terms_en --> The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's - Network accessline 9
The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's - Network accessline 34
The first call `render_preview(scene_url="https://render.janction.jp/samples/cube_scene.py", environment="compare")` checks the
plugins/janction-render/skills/janction-render/references/examples.md
- Network accessline 8
- "Is the render service connected?" -> `render_preview(scene_url="https://render.janction.jp/samples/cube_scene.py", environment="compare")`.
skills/janction-render/SKILL.md
- Network accessline 8
<!-- terms:skill_terms_en --> The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's - Network accessline 9
The `janction-render` MCP server (`https://render.janction.jp/mcp`) renders Blender scenes with Cycles or EEVEE on JANCTION's - Network accessline 34
The first call `render_preview(scene_url="https://render.janction.jp/samples/cube_scene.py", environment="compare")` checks the
skills/janction-render/references/examples.md
- Network accessline 8
- "Is the render service connected?" -> `render_preview(scene_url="https://render.janction.jp/samples/cube_scene.py", environment="compare")`.
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: 8 facts
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:8Low confidence
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:9Low confidence
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:34Low confidence
- Network access in prose of documentationjanction-render/references/examples.md:8Low confidence
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:8Low confidence
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:9Low confidence
- Network access in prose of the SKILL.mdjanction-render/SKILL.md:34Low confidence
- Network access in prose of documentationjanction-render/references/examples.md:8Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/janction-render/skills/janction-render/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/janction-render/skills/janction-render/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/janction-render/skills/janction-render/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/janction-render/skills/janction-render/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.