Jupyter AI

Jupyter AI adds an AI chat interface and agent capabilities to JupyterLab notebooks.

github.com/jupyterlab/jupyter-ai
Jupyter AI homepage screenshot

About Jupyter AI

Jupyter AI is an open source extension that connects AI agents to computational notebooks in JupyterLab. It provides a chat interface that works with installed agents such as Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode through the Agent Client Protocol, with agents detected when their dependencies are installed.

Agents can read and write files, run terminal commands, and interact with notebooks through a built-in Jupyter MCP server, with approval prompts before file writes or command execution. It supports multiple concurrent chats, drag-and-drop of files or notebook cells as context, real-time collaboration with other users on the same server, and custom MCP servers and AI personas via the entry points API.

Key features

  • Chat interface in JupyterLab for AI agents via ACP
  • Support for Claude, Copilot, Gemini, Goose, Kiro and others
  • Agents can read and write files and run terminal commands
  • Notebook interaction through built-in Jupyter MCP server
  • Approval prompts before file writes or command execution
  • Multiple concurrent chats with file or cell context
Best for: JupyterLab users who want to use AI agents with notebooks, files, and terminal commands.
Good for
  • Open source under BSD-3-Clause license
  • Works with multiple agents via ACP and MCP open standards
  • Includes approval prompts for file writes and command execution

Jupyter AI at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

Jupyter AI alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Chatbots & Assistants

Well-known listings from the same topic.

All 238

Jupyter AI FAQ

How do agents become available in Jupyter AI?
Agents are automatically detected when their dependencies are installed alongside Jupyter AI.
What can agents do in JupyterLab?
Agents can read and write files, run terminal commands, and interact with notebooks through the built-in Jupyter MCP server.
Can I extend what agents can access?
Custom MCP servers can be added to provide domain-specific tools, resources, and prompts.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing