Jupyter AI

What is Jupyter AI?

Jupyter AI is an open source extension that connects AI agents to JupyterLab and its notebooks. A chat icon in the side panel opens shared chats, saved as .chat files, where you address one or more AI personas. A persona can wrap an external agent through the Agent Client Protocol, with Claude, Codex, GitHub Copilot, Goose, Kilo, Kiro, Mistral Vibe and OpenCode named in the docs, and the chat shows each agent's models, modes, effort setting and token counts. Notebook tools exposed through a Jupyter MCP server let agents inspect cells, edit files and run notebooks, and by default they ask permission before writing files, running commands or calling MCP tools. You can drag files or notebook cells into the chat, use the @file command, insert returned code into cells, add custom MCP servers and build your own personas. Several users can chat together, and the project is free to install.

Use cases

• Chat with coding agents inside JupyterLab
• Write and debug notebook cells with AI
• Attach notebook cells as chat context
• Collaborate with teammates in shared AI chats
• Add custom MCP tools for domain work
• Call Amazon Bedrock models from notebooks

Who it's for

• Data scientists
• Researchers
• Python developers
• Jupyter administrators

Why use Jupyter AI

• Keeps AI help inside the notebook environment so you do not copy code between a chatbot and JupyterLab.
• Works with several agents through one protocol rather than tying you to a single assistant.
• Permission prompts keep you in control of file writes, commands and tool calls.
• Shared chats let a team see and join the same conversation about a notebook.
• Open source and extensible, so teams can add MCP servers or write their own personas.

Jupyter AI features

• Chat panel inside JupyterLab with multiple chats saved as .chat files
• Agent Client Protocol support for external agents
• Persona picker with model, mode and effort selection
• Jupyter MCP server exposing notebook operations as tools
• Permission prompts before writing files, running commands or using MCP tools
• Drag-and-drop attachments and the @file command
• Code toolbar to copy, insert above or below, or replace a cell
• Custom MCP servers over stdio or HTTP via mcp_settings.json
• Plugin API for building custom personas
• Amazon Bedrock models, custom ARNs and cross-region inference

Jupyter AI integrations

• Claude
• Codex
• GitHub Copilot
• Goose
• Kilo
• Kiro
• Mistral Vibe
• OpenCode
• Amazon Bedrock
• vLLM
• MCP

How to get started with Jupyter AI

1. Install Jupyter AI into your JupyterLab environment by following the Getting Started guide.
2. Click the chat icon in the left panel and create a new chat, which is stored as a .chat file.
3. Pick an AI persona and model, then attach files or notebook cells for context.
4. The persona forwards your message to the connected agent, which may call notebook tools and asks permission where needed.
5. Review the streamed reply, then copy or insert returned code into a notebook cell.

Jupyter AI limitations

• Runs inside JupyterLab only
• External agents need their own dependencies installed and may need their own accounts or API keys
• Bedrock models must be enabled in the AWS console before they appear
• Model usage costs come from whichever provider or agent you connect

Jupyter AI pricing

Jupyter AI is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Jupyter AI alternatives

The main Jupyter AI alternatives listed on Debuly are GitHub Copilot, Cursor, OpenBitFun, Qwen Code, Kilo Code and Google Antigravity. The table compares pricing and platforms; order is A–Z.

1. 

   Cursor

   AI code editor and coding agent with cloud agents, Bugbot code review and multi-provider models, sold with Grok and X plans.

   CodingAutomation and agentsDeveloper platforms
   FreemiumVisit Cursor (official site)
2. 

   GitHub Copilot

   GitHub's AI coding assistant for code completion, chat and agents in VS Code, JetBrains, Visual Studio, the CLI and GitHub.com.

   CodingAutomation and agents
   FreemiumVisit GitHub Copilot (official site)
3. 

   Google Antigravity

   Google's agent-first development platform with a desktop app, CLI, IDE extensions and Python SDK for running coding agents.

   CodingAutomation and agentsDeveloper platforms
   FreemiumVisit Google Antigravity (official site)
4. 

   Kilo Code

   Open-source AI coding agent for VS Code, JetBrains and the CLI, with 500+ models, bring-your-own-key and team plans.

   CodingDeveloper platformsAutomation and agents
   FreemiumVisit Kilo Code (official site)
5. OB

   OpenBitFun

   Open-source agent workspace with a Rust runtime, four agent modes, Mini Apps, and remote control of your desktop sessions from a phone.

   CodingAutomation and agentsDeveloper platforms
   Open sourceVisit OpenBitFun (official site)
6. 

   Qwen Code

   Free open-source coding agent from the Qwen team that runs in a terminal, IDE, desktop app or chat and works with many model providers.

   CodingDeveloper platformsAutomation and agents
   Open sourceVisit Qwen Code (official site)

Jupyter AI FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from jupyter-ai.readthedocs.io · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.