whereismyai
Jupyter AI
Jupyter AI is an open source extension that connects AI agents to computational notebooks in JupyterLab.
Jupyter AI brings agentic AI to JupyterLab by providing a native chat interface to collaborate with frontier AI agents. It integrates models like Claude, Codex, GitHub Copilot, Gemini, Goose, Kiro, Mistral Vibe, and OpenCode through the Agent Client Protocol. Agents can read and write files, run terminal commands, and interact with notebooks using a built-in Model Context Protocol server. A permission system ensures users approve agent actions before they execute files or commands. Developers can also add custom MCP servers and build custom AI personas using entry points.
Jupyter AI at a glance
- Best for: Software engineer, Researcher
- Runs on: Web, self-hosted, open source
- Pricing: Free
- Released: February 2023
- Category: AI coding tool
- Website: github.com/jupyterlab/jupyter-ai
Key features
- Native chat UI for JupyterLab
- Integration with frontier AI agents
- File reading and writing by agents
- Terminal command execution
- Built-in Jupyter MCP server support
- Permission system for agent actions
- Custom MCP server integration
Use it for
- Collaborate with frontier AI agents in notebooks
- Run terminal commands and manage files using agents
- Build and register custom AI personas
- Connect domain-specific tools via custom MCP servers
Companions
Tools that articles about Jupyter AI recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to Jupyter AI
- Mito — Automates Excel reporting and Python scripting without leaving the notebook environment.
- Runcell — It works directly inside Jupyter notebooks to execute code and read outputs.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Cursor — Autocomplete, inline edits and parallel agents in one editor
- CopilotKit — Connects your application to AI agents with generative UI and human approvals.
- Magpie — It enables AI agents to use models not natively supported by their internal protocols.
- CocoIndex — Maintains fresh context for AI agents with minimal incremental processing.
- Factorai — Manages multiple independent AI coding agents in parallel from one interface.
- Agent Cockpit — It checks evidence chains deterministically so broken claims never slip by unnoticed.
- ZCode — Integrates GLM-5.3 with multi-agent workflows and remote chat control.
- AG-UI — Standardizes agent-user interactions and generative UI for applications.
- PI Desktop — It keeps projects, settings, and sessions local without mandatory accounts.
All Jupyter AI alternatives