by datalayer
🪐 🤖 AI Agents for JupyterLab with 🔧 MCP tools - Chat interface for optimized notebook interaction and code execution.
# Add to your Claude Code skills
git clone https://github.com/datalayer/jupyter-ai-agents🪐 ✨ AI Agents for JupyterLab with 🛠️ MCP tools - Chat interface for intelligent notebook interaction, code execution, and workspace management.
Experience seamless AI-powered assistance directly within JupyterLab through our intuitive chat interface:

The chat interface is built using Pydantic AI for robust AI agent orchestration and Vercel AI Elements for the user interface components.
By default, the Jupyter MCP Server is started as a Jupyter server extension, providing access to all Jupyter MCP server tools directly through the chat interface. This enables the AI agent to interact with notebooks, execute code, manage files, and perform various Jupyter operations seamlessly.

Currently, we support Anthropic Claude Sonnet 4.0 as the AI model. To get started:
Set up your environment:
export ANTHROPIC_API_KEY='your-api-key-here'
Install Jupyter AI Agents:
pip install jupyter_ai_agents
pip uninstall -y pycrdt datalayer_pycrdt
pip install datalayer_pycrdt==0.12.17
Launch JupyterLab with the required configuration:
jupyter lab
Access the chat interface through the right panel in JupyterLab.
We're actively working on expanding the capabilities of Jupyter AI Agents:
Check out our GitHub Issues to see what we're working on. Contributions are welcome!
Note: The documentation at https://jupyter-ai-agents.datalayer.tech will be updated soon to reflect the new chat features and capabilities.