Run Agent-Assisted Notebook Workflows in JupyterLab With Notebook Intelligence
Use Notebook Intelligence to add chat, inline edit, autocomplete, MCP tools, Claude Code mode, and coding-agent launchers directly inside JupyterLab.
Prerequisites
Python environment with JupyterLab, notebook-intelligence, optional Node.js for Claude Code and MCP server launchers, and an LLM provider such as GitHub Copilot, OpenAI-compatible/LiteLLM endpoint, Ollama, or Claude Code
Installation
Install or set up from the source-backed instructions:
Install with pip install notebook-intelligence, restart JupyterLab, open the NBI panel, configure a provider or enable Claude mode, and optionally add MCP servers in ~/.jupyter/nbi/mcp.json or use launcher tiles for installed agent CLIs.