Jupyter AI

Free

An open-source, configurable AI assistant in Jupyter Notebook and JupyterLab that supports 100+ LLMs, including locally-hosted models from Ollama and GPT4All. #opensource

FreeFree tier

Inputs: text, fileOutputs: text, code

Type

Open Source

Visit Website GitHub (40 stars)

About Jupyter AI

Jupyter AI is an open-source extension that connects AI agents to computational notebooks in JupyterLab. It provides a native chat UI for collaborating with frontier AI agents—including Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode—integrated through the Agent Client Protocol (ACP). Agents are automatically detected when their dependencies are installed. They can read and write files, run terminal commands, and interact with notebooks via a built-in Jupyter MCP server. A permission system requires agent approval before writing files or executing commands. Users can create multiple concurrent chats, drag and drop files or notebook cells as context, and collaborate in real time with others on the same server. Jupyter AI is extensible: custom MCP servers can be added for domain-specific tools, and developers can register custom AI personas via the entry points API. Built on open standards, it avoids vendor lock-in.

Key Features

Native chat UI for collaborating with AI agents

Support for frontier AI agents via Agent Client Protocol (ACP): Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, OpenCode

Automatic detection of installed agent dependencies

Agents can read and write files, run terminal commands, and interact with notebooks through built-in Jupyter MCP server

Permission system with user approval for file writes and command execution

Multiple concurrent chats and drag-and-drop context (files or notebook cells)

Real-time collaboration with other users on the same server

Extensible: add custom MCP servers for domain-specific tools and resources

Developer API to build and register custom AI personas via entry points

Built on open standards (ACP and MCP) to avoid vendor lock-in

Pros & Cons

Pros

Open-source with permissive BSD-3-Clause license
Supports multiple frontier AI agents via open standard (ACP)
Permission system provides safety and control over agent actions
Extensible through custom MCP servers and developer API
Real-time collaboration enables team-based AI workflows
No vendor lock-in due to open standards

Cons

Requires installing separate agent packages for each AI provider
Permission system may slow down workflow for users who prefer full automation
Relatively new (under incubation) – ecosystem and documentation still evolving

Best For

Collaborating with AI agents on data analysis and notebook workflowsAutomating code writing, file manipulation, and terminal commands with safety guardrailsBuilding custom AI assistants for domain-specific research or development tasksReal-time collaborative AI-powered coding sessions in JupyterLab

FAQ

What agents does Jupyter AI support?

Jupyter AI supports frontier AI agents including Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode, all integrated via the Agent Client Protocol (ACP).

Is Jupyter AI free to use?

Yes, Jupyter AI is open-source and free. It is licensed under BSD-3-Clause. Some agents may have their own pricing.

Can I add my own custom tools or servers?

Yes, you can add custom MCP servers to give agents access to domain-specific tools, resources, and prompts. Developers can also build and register custom AI personas using the entry points API.