charly-jupyter
Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).
By opencharlyLicense: MIT0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 16 skill or MCP entries
- Source updated
- Aug 28, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install plugin
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add charly-jupyter@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/opencharly/marketplaceClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is jupyter/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/jupyter/SKILL.md├── skills/jupyter-layer/SKILL.md├── skills/jupyter-mcp/SKILL.md├── skills/jupyter-ml/SKILL.md├── skills/jupyter-ml-layer/SKILL.md├── skills/jupyter-ml-notebook/SKILL.md├── skills/llama-cpp/SKILL.md├── skills/notebook-finetuning/SKILL.md├── skills/notebook-llm-on-supercomputers/SKILL.md├── skills/notebook-ollama/SKILL.md├── skills/notebook-openrouter/SKILL.md├── skills/notebook-templates/SKILL.md├── skills/unsloth/SKILL.md├── skills/unsloth-studio/SKILL.md├── skills/unsloth-studio-layer/SKILL.md└── .mcp.json
Included Skills15
Lightweight JupyterLab with real-time collaboration on port 8888. No GPU required. Based on fedora (not nvidia), supports both amd64 and arm64. MUST be invoked before building, deploying, configuring, or troubleshooting the jupyter box.
Lightweight JupyterLab with real-time collaboration (jupyter-collaboration) on port 8888. No GPU required. Use when working with collaborative notebooks, jupyter-collaboration, or lightweight Jupyter environments without ML/CUDA dependencies.
JupyterLab CRDT MCP server extension exposing the notebook tools (notebook_*/cell_* + room_list + notebook_list_users) for programmatic notebook access. MUST be invoked when working with: the MCP server implementation, CRDT collaboration, the auto-attach single-room invariant, or the Tier 1 pip-only installation pattern for jupyter extensions.
Full CUDA ML JupyterLab box with real-time collaboration and CRDT MCP server. Base: nvidia. Port 8888. GPU-accelerated ML training + collaborative notebooks. MUST be invoked before building, deploying, or troubleshooting the jupyter-ml box.
Full CUDA ML stack + JupyterLab with real-time collaboration and CRDT MCP server on port 8888. Use when working with GPU-accelerated Jupyter notebooks, ML training with collaboration, or the jupyter-ml candy.
Full CUDA ML JupyterLab box with finetuning, Ollama, and LLM course notebooks, CRDT MCP server, and real-time collaboration. Base: nvidia. Port 8888. Combines jupyter-ml with 37 Unsloth fine-tuning notebooks, 6 Ollama integration notebooks, and 15 LLM course notebooks. MUST be invoked before building, deploying, or troubleshooting the jupyter-ml-notebook box.
llama.cpp prebuilt binaries and GGUF conversion tools. Use when working with llama.cpp, GGUF model conversion, or llama-quantize/llama-cli.
Unsloth fine-tuning notebook collection provisioned into the workspace volume at deploy time. Data-only candy — no packages, no services, no dependencies. Use when working with notebook-finetuning, Unsloth training notebooks, or unsloth-studio data provisioning.
LLMs on Supercomputers course notebook collection (TU Wien AI Factory Austria). 15 Jupyter notebooks covering prompt engineering, RAG, and fine-tuning. Data-only candy — no packages, no services, no dependencies. Use when working with the LLM course notebooks, LangChain tutorials, or RAG examples.
Ollama integration notebook collection provisioned into the workspace volume at deploy time. 6 Jupyter notebooks demonstrating Ollama via requests, OpenAI, ollama lib, Anthropic, HuggingFace, and GPU. Data-only candy — no packages, no services, no dependencies. Use when working with notebook-ollama, Ollama API tutorials, or Jupyter+Ollama integration.
OpenRouter API integration notebook collection provisioned into the workspace volume at deploy time. 3 Jupyter notebooks demonstrating OpenRouter API basics, model discovery, and practical inference. Data-only candy with env_require — first candy to use the env_require feature. Use when working with notebook-openrouter, OpenRouter API tutorials, or Jupyter+OpenRouter integration.
Starter notebook templates provisioned into the workspace volume at deploy time. First data-only candy in the project — no packages, no services, no dependencies. Use when working with notebook-templates, data candies, or jupyter initial content.
Unsloth LLM fine-tuning library with vLLM integration. Tier 1 post-install layer — no pixi.toml, requires pixi env from a parent candy (python-ml, jupyter-ml, unsloth-studio). Use when working with Unsloth, LLM fine-tuning, or vLLM wheel installation.
Unsloth Studio fine-tuning web UI with CUDA GPU support, vLLM inference, and llama.cpp. Runs as a supervisord service on ports 8888 (Studio) and 8000 (vLLM API). MUST be invoked before building, deploying, configuring, or troubleshooting the unsloth-studio box.
Unsloth Studio fine-tuning web UI on ports 8888/8000 with vLLM inference. Tier 2 environment-owner meta-layer composing llama-cpp + unsloth, owns pixi.toml. Use when working with Unsloth Studio, the fine-tuning web UI, or the unsloth-studio box.
MCP servers1
- url
- http://localhost:8888/mcp
Plugin manifests2
{
"name": "charly-jupyter",
"description": "Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).",
"author": {
"name": "opencharly"
},
"repository": "https://github.com/opencharly/marketplace",
"skills": "./skills/",
"interface": {
"displayName": "OpenCharly Jupyter",
"shortDescription": "Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).",
"longDescription": "Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).",
"developerName": "opencharly",
"category": "images",
"capabilities": [
"Instructions"
],
"defaultPrompt": [
"Use OpenCharly Jupyter for this OpenCharly task."
]
},
"mcpServers": "./.mcp.json"
}{
"name": "charly-jupyter",
"description": "Self-contained skills + MCP wiring for the jupyter image family (jupyter, jupyter-ml, jupyter-ml-notebook, unsloth-studio). Ships the jupyter MCP server (port 8888).",
"author": {
"name": "opencharly"
},
"homepage": "https://github.com/opencharly/charly",
"repository": "https://github.com/opencharly/marketplace",
"license": "MIT",
"keywords": [
"charly",
"jupyter",
"notebooks",
"mcp",
"collaboration",
"ml"
],
"mcpServers": "./.mcp.json"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[charly-jupyter on Agent Plugins Marketplace](https://pluginsmp.com/plugins/charly-jupyter)