# raphaelmansuy/edgequake

EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation

Repository: https://github.com/raphaelmansuy/edgequake
Canonical: https://ross.abutalabs.com/products/edgequake
Homepage: https://edgequake.com
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: graphrag, knowledge-graph, lightrag, rag
Last push: 2026-08-25T13:18:35+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 18
- inputs: {"age_days": 255, "days_push": 8, "days_rel": 8, "gap_med": 0.0, "n_releases_24m": 75}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2078, forks 243 (observed 2026-08-28T04:06:11.419033+00:00)

## What it is
EdgeQuake is a high-performance Graph-RAG framework written in Rust, inspired by LightRAG, that transforms documents (PDFs, markdown, text) into knowledge graphs for retrieval-augmented generation. It ships as a full self-hosted stack with a REST API, Web UI, PostgreSQL-backed graph (AGE) and vector (pgvector) storage, and six retrieval modes.

## Use cases
- build a graphrag pipeline over my pdf documents
- extract entities into a knowledge graph for better rag answers
- self-host a lightrag alternative without python
- query documents with hybrid vector and graph retrieval
- run multi-tenant rag with source traceability
- integrate a graph-based retriever into langchain or open webui
- ingest multi-column pdfs into a searchable knowledge base

## When to choose
- you want Graph-RAG quality with Rust performance instead of Python pipeline fragility
- you need entity relationships, lineage, and provenance in retrieval results
- you want self-hosting with PostgreSQL, pgvector, and Apache AGE
- you need multi-tenancy, ingestion cancellation, and production operational features
- you prefer Docker quickstart deployment with OpenAI or Ollama providers

## When to avoid
- you only need simple vector similarity search without graph structure
- you cannot run PostgreSQL or Docker in your environment
- you need a lightweight embedded library rather than a full service stack
- your team depends on a mature ecosystem with long-term stability guarantees
- you want a fully managed cloud service

## Facets
- artifact type: service
- maturity: active
- function: rag, search-engine, vector-database, nlp, machine-learning, pdf, api-framework, http-server
- domain: large-language-models, artificial-intelligence, pdf, self-hosted
- platform: rust, self-hosted, windows, cross-platform
- tags: graphrag, knowledge-graph, lightrag-inspired, entity-extraction, pgvector, postgresql-age, hybrid-retrieval, multi-tenancy, pdf-ingestion, openai, ollama, langchain-integration, open-webui, retrieval-augmented-generation, search, natural-language-processing, docker, web-server, linux, macos

## Member repositories
- raphaelmansuy/edgequake (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.419033+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 2026-08-30T02:56:07.898891+00:00, confidence not recorded.
  - readme: https://github.com/raphaelmansuy/edgequake (fetched 2026-08-28T04:06:11.419033+00:00, sha 314304179076)
  - homepage: https://edgequake.com (fetched 2026-08-29T10:36:23.422392+00:00, sha a98387930485)
  - site_page: https://edgequake.com/docs (fetched 2026-08-29T10:36:23.431549+00:00, sha 14e992364753)
  - site_page: https://edgequake.com/docs/getting-started (fetched 2026-08-29T10:36:23.433561+00:00, sha 2ec7f14c439b)
  - site_page: https://edgequake.com/docs/concepts (fetched 2026-08-29T10:36:23.436151+00:00, sha e1a3c048741b)
  - site_page: https://edgequake.com/docs/deep-dives (fetched 2026-08-29T10:36:23.438406+00:00, sha 0c2a1440dace)
  - site_page: https://edgequake.com/docs/operations (fetched 2026-08-29T10:36:23.440240+00:00, sha b6ca49160797)
  - site_page: https://edgequake.com/docs/integrations (fetched 2026-08-29T10:36:23.441934+00:00, sha 85d5a9cb37f8)
  - site_page: https://edgequake.com/docs/api-reference (fetched 2026-08-29T10:36:23.443629+00:00, sha 8651b2807342)
- Data as of 2026-08-30T08:39:29.467469+00:00.