{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/7"}],"enrichment":{"capability":"Jupyter AI is a JupyterLab extension that integrates agentic AI into computational notebooks, enabling collaboration with frontier AI agents through a native chat UI with file and command execution capabilities.","skillfed_tags":["jupyter-extension","agent-protocol","notebook-ai"],"use_cases":["Pair-program with AI agents in notebooks, having them write and debug code with your approval.","Delegate file operations and terminal commands to agents while maintaining control through a permission system.","Build domain-specific agent capabilities by adding custom MCP servers for specialized tools and data access.","Collaborate with teammates in real time on the same notebook server with shared AI agent chats.","Extend agent functionality by creating custom AI personas using the entry points API."],"what_it_does":"Jupyter AI extends JupyterLab with a native chat interface that connects to agentic AI systems through the Agent Client Protocol (ACP) and Model Context Protocol (MCP). It allows you to collaborate with frontier AI agents\u2014including Claude, Codex, GitHub Copilot, Gemini, and others\u2014directly within your computational notebooks. Agents can read and write files, execute terminal commands, and interact with notebooks through a built-in MCP server, all governed by a permission system that requires approval before sensitive actions.\n\nThe extension is designed for flexibility and extensibility. You can add custom MCP servers to give agents access to domain-specific tools and resources, create multiple concurrent chats, drag and drop files or notebook cells as context, and collaborate in real time with other users on the same server. By building on open standards like ACP and MCP, it avoids vendor lock-in and integrates with the broader ecosystem of compatible agents and tools.","worth_installing":"Yes. Jupyter AI is actively maintained, has low install friction, carries a permissive BSD license, and integrates cleanly into JupyterLab 4 with modern Python support (3.9\u20133.13). It fills a genuine need for agentic AI in notebooks and avoids vendor lock-in through open standards. Install it if you use JupyterLab and want AI agent collaboration; the modular design means you only pay for what you use."},"id":"jupyter-ai","links":{"html":"https://skillfed.io/packages/jupyter-ai","md":"https://skillfed.io/packages/jupyter-ai.md","pypi":"https://pypi.org/project/jupyter-ai/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-14","license_spdx":null,"license_treatment":"permissive","name":"jupyter-ai","python_support":"supports_current","summary":"A set of extensions providing agentic AI in JupyterLab"},"popularity":{"monthly_downloads":199091,"position":9716,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"3.1.3"}