在 JupyterLab 中使用 Notebook Intelligence 运行代理辅助的笔记本工作流
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
Use the upstream install or setup path that matches your environment:
- pip install notebook-intelligence
Requirements and caveats from upstream:
- Python 3.10+
- Node.js — only required for Claude mode (the Claude Code CLI) and for MCP servers that launch via npx.
- A fresh virtualenv or conda env is recommended so NBI doesn't conflict with system Python.
Basic usage or getting-started notes:
- Quick start
- MCP config example
- JupyterLab 4.x
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/plmbr/notebook-intelligence/HEAD/README.md
Documentation
- https://nbi.plmbr.dev
