A Neovim plugin that brings AI chat, inline code edits and coding agents into the editor, with support for many LLM providers.
jupyterlab/jupyter-ai
An open source JupyterLab extension that adds a chat UI for connecting AI agents like Claude, Codex, and Gemini to notebooks.
Open-source alternative to:GitHub Copilot
- Stars
- 4,438
- Forks
- 541
- Open issues
- 324
- Last commit
- 17 hours ago
What is it?
Jupyter AI adds agentic AI to JupyterLab through a native chat panel. It connects agents such as Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode via the Agent Client Protocol (ACP). Agents are detected automatically once their dependencies are installed.
Agents can read and write files, run terminal commands, and work with notebooks through a built-in Jupyter MCP server. A permission system requires approval before an agent writes files or executes commands. Users can run multiple concurrent chats, drag files or notebook cells in as context, and collaborate in real time with others connected to the same server.
The project supports custom MCP servers for domain-specific tools, resources, and prompts. Developers can build and register their own AI personas through the entry points API. It is licensed under BSD-3-Clause and is incubating under the JupyterLab organization.
Key features
- 01Native chat UI inside JupyterLab with multiple concurrent chats.
- 02Agents auto-detected once their dependencies are installed.
- 03Agents can read/write files, run terminal commands, and operate notebooks via a built-in MCP server.
- 04Approval prompts before agents write files or execute commands.
- 05Custom MCP servers and developer-defined AI personas via entry points.
Use cases
- Getting help writing or debugging analysis code in a Jupyter notebook.
- Letting an agent edit project files and run commands while you review each action.
- Collaborating with teammates on a shared JupyterLab server with AI assistance.
- Connecting notebooks to domain-specific tools through custom MCP servers.
In collections
Topics
FAQ
- What is jupyter-ai?
- An open source JupyterLab extension that adds a chat UI for connecting AI agents like Claude, Codex, and Gemini to notebooks. Jupyter AI adds agentic AI to JupyterLab through a native chat panel. It connects agents such as Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode via the Agent Client Protocol (ACP). Agents are detected automatically once their dependencies are installed.
- Is jupyter-ai free to use? What license does it have?
- jupyter-ai is open source under the BSD-3-Clause license. Check the license terms before using it in commercial products.
- Is jupyter-ai still maintained?
- Actively maintained. The last commit to jupyter-ai was on Nov 6, 2026.
- What can I use jupyter-ai for?
- Getting help writing or debugging analysis code in a Jupyter notebook. Letting an agent edit project files and run commands while you review each action. Collaborating with teammates on a shared JupyterLab server with AI assistance. Connecting notebooks to domain-specific tools through custom MCP servers.
- Where can I get jupyter-ai?
- The source code and installation instructions are on GitHub: https://github.com/jupyterlab/jupyter-ai
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An extensible, browser-based interactive computing environment that brings notebooks, terminals, editors and file browsing into one workspace.
Ready-to-run Docker images bundling JupyterLab, Jupyter Notebook and common scientific Python tools for personal or team use.
A JupyterLab distribution that runs entirely in the browser, using WebAssembly-based Python kernels with no server required.
A JupyterLab extension that adds a Git panel for staging, committing, branching, and syncing repositories from within notebooks.
A JupyterLab extension that lets you browse and create new notebooks from a shared library of notebook templates.