Jupyter AI

Active
GitHub Python BSD-3-Clause

Description

An open-source JupyterLab extension that connects AI agents to computational notebooks, enabling code generation, error explanation, and document Q&A.

Key Features

  • Native chat UI for collaborating with frontier AI agents — Claude, Codex, Gemini, Copilot, and more via ACP
  • Built-in Jupyter MCP server enabling agents to read/write files and run terminal commands
  • Permission system with approval gates before file writes or command execution
  • Multiple concurrent chats with drag-and-drop file and notebook cell context
  • Extensible with custom MCP servers for domain-specific tools, resources, and prompts
  • Auto-detection of installed agents — no configuration needed to get started

Use Cases

💡 Generating Python code for data analysis directly within JupyterLab notebooks
💡 Getting AI-powered explanations for cell errors and tracebacks in real time
💡 Asking natural language questions about uploaded documents and datasets
💡 Building custom AI personas with domain-specific MCP tool integrations
💡 Collaborating with team members on shared notebooks with AI assistance

Tags

python agent tools llm data-processing

Categories

📚 RAG Tools

Quick Start

Install with 'pip install jupyter-ai' and open JupyterLab. Agents are auto-detected when dependencies are installed — just pick your preferred agent and start chatting. Use the drag-and-drop feature to add notebook cells as context. Configure custom MCP servers in settings for domain-specific tools.
Visit GitHub Visit Website View Docs

Related Projects