# circlemind-ai/fast-graphrag

RAG that intelligently adapts to your use case, data, and queries

Repository: https://github.com/circlemind-ai/fast-graphrag
Canonical: https://ross.abutalabs.com/products/fast-graphrag
Language: Python
License: MIT
License Family: permissive
Last push: 2025-11-01T20:45:25+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 50, release rhythm 35, longevity 48
- inputs: {"age_days": 672, "days_push": 305, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3849, forks 248 (observed 2026-08-28T04:08:24.205438+00:00)

## What it is
fast-graphrag is a Python library providing a streamlined, promptable GraphRAG framework for interpretable, high-precision retrieval workflows built on knowledge graphs. It uses PageRank-based graph exploration, supports incremental updates, and is designed to be fast and low-cost compared to alternatives like Microsoft's graphrag.

## Use cases
- build a graph-based RAG pipeline over my documents
- query unstructured text with knowledge graph retrieval
- cheaper alternative to Microsoft graphrag
- incrementally update a knowledge graph as data changes
- visualize and debug extracted knowledge from documents
- add interpretable retrieval to an LLM application

## When to choose
- you want graph-based RAG with interpretable, navigable knowledge
- cost and speed matter more than heavyweight agentic orchestration
- your data evolves and you need incremental graph updates
- you want a typed, async Python library that fits into an existing pipeline

## When to avoid
- you need simple vector-only semantic search without graph structure
- you want a turnkey hosted RAG service rather than a library
- your stack is not Python
- you need a battle-tested, long-established solution with large ecosystem support

## Facets
- artifact type: library
- maturity: active
- function: rag, llm-inference, search-engine, agent-framework, nlp
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: graphrag, knowledge-graph, pagerank, retrieval-pipeline, openai, async, retrieval-augmented-generation, natural-language-processing, search

## Member repositories
- circlemind-ai/fast-graphrag (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:24.205438+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:58.894118+00:00, confidence not recorded.
  - readme: https://github.com/circlemind-ai/fast-graphrag (fetched 2026-08-28T04:08:24.205438+00:00, sha 3d06523b9dc9)
- Data as of 2026-08-30T08:39:29.467469+00:00.