Jupyter AI

Jupyter AI is an extension you run with your own JupyterLab server, giving agents access to notebooks, files and terminal commands in that environment. Model access comes from your separately installed agent; Claude Code’s standard connection, for example, sends prompts to its cloud provider. Its built-in Jupyter MCP server connects agents to notebook operations, alongside file editing and terminal commands. Chat sits beside the work.

The interface shows file changes, notebook activity and cell error fixes as they happen. By default, agents ask permission before writing files, running commands or using MCP tools, so you can review actions that change the environment.

Multiple concurrent chats keep separate tasks in their own conversations. Files and notebook cells can serve as attachments, giving agents context from the work you're discussing. Other users connected to the same server can participate in shared chats and collaborate in real time.

Agent Client Protocol (ACP) support connects the extension to Claude, Codex, GitHub Copilot, Goose, Kilo, Kiro, Mistral Vibe and OpenCode. This gives users a choice of compatible agents within the same notebook interface, rather than a separate chat window for each tool.

Developers can register their own AI personas through an entry points API. Custom MCP servers can supply domain-specific tools, resources and prompts, in addition to the built-in notebook tools. Jupyter AI is open source under the BSD-3-Clause license.