# jupyterlab/jupyter-ai

An open source extension that connects AI agents to computational notebooks in JupyterLab.

Repository: https://github.com/jupyterlab/jupyter-ai
Canonical: https://ross.abutalabs.com/products/jupyter-ai
Homepage: https://jupyter-ai.readthedocs.io/
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: jupyter, jupyterlab, jupyterlab-extension, acp, agents
Last push: 2026-08-26T06:07:08+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 92
- inputs: {"age_days": 1301, "days_push": 7, "days_rel": 20, "gap_med": 12.0, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4382, forks 527 (observed 2026-08-28T04:08:46.966377+00:00)

## What it is
Jupyter AI is an open-source JupyterLab extension that connects agentic AI assistants to computational notebooks via the Agent Client Protocol (ACP). It provides a native chat UI, a built-in Jupyter MCP server for file/terminal/notebook actions, and a permission system for agent guardrails.

## Use cases
- chat with AI agents inside JupyterLab notebooks
- let an AI agent edit notebooks and run terminal commands with approval
- add custom MCP servers for domain-specific agent tools
- build custom AI personas for JupyterLab
- collaborate with teammates and AI agents in real time on a shared server

## When to choose
- you use JupyterLab and want agentic AI integrated into your notebooks
- you want vendor-neutral AI agents via open standards like ACP and MCP
- you need permission guardrails over agent file writes and command execution

## When to avoid
- you need AI features in plain Jupyter Notebook or another IDE like VS Code
- you want a standalone AI chat app without a Jupyter server
- you cannot install additional agent dependencies

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, chatbot, mcp, llm-inference, developer-tools
- domain: artificial-intelligence, developer-tools, data-science
- platform: python, cross-platform
- tags: jupyterlab-extension, acp, notebook-ai, ai-agents, mcp-server, chat-ui, jupyter, web-server

## Member repositories
- jupyterlab/jupyter-ai (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.966377+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:17.413892+00:00, confidence not recorded.
  - readme: https://github.com/jupyterlab/jupyter-ai (fetched 2026-08-28T04:08:46.966377+00:00, sha bd69c600c4e2)
  - registry_pypi: https://pypi.org/pypi/jupyter-ai/json (fetched 2026-08-29T09:10:04.184862+00:00, sha 3f5f01eabe72)
- Data as of 2026-08-30T08:39:29.467469+00:00.