graphrag
A modular Retrieval-Augmented Generation system from Microsoft that uses graphs to build context for question answering. The README describes it as a research project.
Share on XLicense: MIT
Overview
GraphRAG is a modular graph-based Retrieval-Augmented Generation system from Microsoft. It is a data pipeline and transformation suite that uses LLMs to pull structured data out of unstructured text, then uses graphs to build a focused context for question answering. The README calls it a research project. It is largely in maintenance mode, with no new features or pull requests, only bug fixes and dependency updates.
Key features
- Extracts structured data from unstructured text using LLMs
- Builds graphs to form targeted context for question answering
- Modular pipeline and transformation suite
- Documentation and an arXiv paper are available
Best for
Researchers and developers who want to study how graphs can improve LLM answers over private text. Expect no new features, since the project is in maintenance mode.
- Upstream
- microsoft/graphrag
- Fork on GitHub
- Guo-astro/graphrag
- Upstream stars
- 36k
- Category
- AI agents and LLM tools
- License
- MIT
- Forked
- 2025-07-15
- Sync status
- Behind upstream
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub