- Protocol
- ACP
- Type
- Tool
- Stars
- 4.4k
- License
- BSD-3-Clause
- Last push
- Nov 7, 2026
by jupyterlabAbout Jupyter AI
Jupyter AI is an open-source ACP tool by jupyterlab, written mainly in Python. JupyterLab extension that integrates coding agents through ACP. It has 4,442 GitHub stars and uses the BSD-3-Clause license, and its code was last pushed on Nov 7, 2026.
New to ACP? Our ACP Protocol guide explains how it works and lists other projects built on it.
At a glance
- Protocol
- ACP
- Type
- Tool
- Language
- Python
- License
- BSD-3-Clause
- GitHub stars
- 4,442
- Last push
- Nov 7, 2026
Listed from public GitHub data, checked 2026-11-08. Not scanned by AgenticMart.
Questions about Jupyter AI
What is Jupyter AI?
JupyterLab extension that integrates coding agents through ACP It is listed as a ACP tool, maintained in the jupyterlab/jupyter-ai repository on GitHub.
How do I install Jupyter AI?
The README in jupyterlab/jupyter-ai has the setup steps. Clone the repository with git clone https://github.com/jupyterlab/jupyter-ai.git and follow its instructions.
Is Jupyter AI an official ACP project?
No. It is a community project built on ACP, not published by the organisation that runs the protocol.
What license does Jupyter AI use?
It is published under the BSD-3-Clause license. Check the license file in the repository before using it commercially.
Is Jupyter AI still maintained?
Its code was last pushed on Nov 7, 2026, and it had 4,442 GitHub stars when we checked on 2026-11-08. Look at recent issues and releases in the repository for a fuller picture.
README
Jupyter AI brings agentic AI to JupyterLab. It provides a native chat UI where you can collaborate with frontier AI agents — including Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode — all integrated through the Agent Client Protocol (ACP). Agents are automatically detected when their dependencies are installed, so getting started is as simple as installing Jupyter AI and the agent of your choice.
Agents in Jupyter AI can read and write files, run terminal commands, and interact with notebooks through a built-in Jupyter MCP server. A permission system gives you guardrails over agent actions — agents request approval before writing files or executing commands. You can also create multiple concurrent chats, drag and drop files or notebook cells as context, and collaborate in real time with other users connected to the same server.
Jupyter AI is designed to be flexible and extensible. You can add custom MCP servers to give agents access to domain-specific tools, resources, and prompts. Developers can build and register their own AI personas using the entry points API. By building on open standards like ACP and MCP, Jupyter AI avoids vendor lock-in and gives you access to the full ecosystem of compatible agents and tools.
Packages
This repository contains two packages, released together:
jupyter-ai: the agent chat for JupyterLab. It includesjupyter-ai-core.jupyter-ai-core: JupyterLab with the extensions that let a coding agent in your terminal work in it.
Quick Links
- Getting Started — installation, agent setup, and first chat
- User Guide — chat features, notebook tools, and custom MCP servers
- Contributor Guide — how to contribute to Jupyter AI
- Developer Guide — building custom agents and MCP servers
- Troubleshooting — common issues and solutions
Governance
Jupyter AI is currently under incubation as part of the JupyterLab organization.
More ACP projects
All 20 →
CodeCompanion
Neovim AI coding plugin with built-in ACP support
Agent Client Protocol
Specification, schema and Rust crate for connecting editors to agents
Toad
Terminal interface for AI coding agents that speaks ACP