TaskWeaver is a Microsoft code-first agent framework for data analytics tasks. 6.1K+ stars. Planning, stateful execution, DataFrames, plugins. MIT.
This block should tell both the user and the agent what to copy, install, and apply first.
git clone https://github.com/microsoft/TaskWeaver.git
cd TaskWeaver
pip install -r requirements.txt
# Configure LLM in taskweaver_config.json
# Then run
python -m taskweaver -p ./project/Requires Python >= 3.10.
TaskWeaver is a Microsoft code-first agent framework for planning and executing data analytics tasks. With 6,100+ GitHub stars and MIT license, it interprets user requests through generated code, coordinates plugins, supports complex task decomposition with progress tracking, stateful execution preserving chat and code history, rich data structures (DataFrames), code verification before execution, customizable domain-specific plugins, and multiple interfaces (CLI, web UI, library).
Best for: Data analysts and engineers wanting AI-powered data analytics workflows Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
Q: What is TaskWeaver? A: Microsoft code-first analytics agent with 6.1K+ stars. Planning, stateful execution, DataFrames, plugins. MIT.
Q: How do I install TaskWeaver? A: Clone repo, pip install -r requirements.txt, configure LLM, run python -m taskweaver.
Created by Microsoft. MIT. microsoft/TaskWeaver — 6,100+ GitHub stars