datalayer/jupyter-ai-agents
🪐 🤖 AI Agents for JupyterLab with 🔧 MCP tools - Chat interface for optimized notebook interaction and code execution.
Built on **Pydantic AI** for agent orchestration and **Model Context Protocol (MCP)** for tool integration, it exposes Jupyter operations (code execution, file management, notebook manipulation) directly to LLM agents via the Jupyter MCP Server. Supports multiple LLM providers including OpenAI, Anthropic, Azure OpenAI, Google, Bedrock, and others through a unified model specification format, with both interactive chat and CLI modes (prompt agent, error explanation, REPL) for notebook automation.
138 stars. Available on PyPI.
Stars
138
Forks
16
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Feb 01, 2026
Commits (30d)
0
Dependencies
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/datalayer/jupyter-ai-agents"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
mims-harvard/ToolUniverse
Democratizing AI scientists with ToolUniverse
cryxnet/DeepMCPAgent
Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.
dhyansraj/mcp-mesh
Enterprise-grade distributed AI agent framework | Develop → Deploy → Observe | K8s-native |...
namastexlabs/pgserve
Embedded PostgreSQL 18 server with true concurrent connections - zero config, auto-provision databases
yutori-ai/yutori-mcp
Yutori MCP