# FalkorDB/FalkorDB

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

Repository: https://github.com/FalkorDB/FalkorDB
Canonical: https://ross.abutalabs.com/products/falkordb
Homepage: https://www.falkordb.com/
Language: Rust
License: NOASSERTION
License Family: other
Topics: graph-database, knowledge-graph, database-as-a-service, cloud-database, database, developer-tools, devtools, realtime-database, graphrag
Last push: 2026-08-26T22:56:12+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 81
- inputs: {"age_days": 1140, "days_push": 7, "days_rel": 13, "gap_med": 6, "n_releases_24m": 68}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5660, forks 436 (observed 2026-08-28T04:09:27.242626+00:00)

## What it is
FalkorDB is an ultra-fast, multi-tenant property graph database built on GraphBLAS sparse adjacency matrices, queryable via OpenCypher with full-text, vector, and range indexes. It is purpose-built for GraphRAG, agent memory, and real-time graph analytics for GenAI applications, available self-hosted or as a managed cloud service.

## Use cases
- build a graphrag pipeline for llm applications
- store and query a knowledge graph with cypher
- give chatbots long-term agent memory
- detect fraud rings by analyzing entity relationships
- run low-latency graph queries for real-time recommendations
- combine graph traversal with vector search for agentic ai

## When to choose
- you need a low-latency graph database optimized for GraphRAG and LLM grounding
- you want OpenCypher support with vector and full-text indexes in one engine
- you need multi-tenant graph storage with graph-level access control
- you want to self-host via Docker or use a managed cloud

## When to avoid
- you need a permissive open-source license (it uses SSPL)
- your workload is simple relational data without complex relationships
- you require a fully open-source managed alternative without vendor cloud ties

## Facets
- artifact type: service
- maturity: active
- function: database, vector-database, search-engine, rag
- domain: databases, large-language-models, artificial-intelligence, developer-tools
- platform: cloud, self-hosted, rust
- tags: graph-database, graphrag, knowledge-graph, opencypher, sparse-matrices, graphblas, multi-tenant, agent-memory, redis-based, property-graph, retrieval-augmented-generation, linux, docker

## Member repositories
- FalkorDB/FalkorDB (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.242626+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 2026-08-29T17:54:20.363056+00:00, confidence not recorded.
  - readme: https://github.com/FalkorDB/FalkorDB (fetched 2026-08-28T04:09:27.242626+00:00, sha fab2a03deb2a)
  - homepage: https://www.falkordb.com/ (fetched 2026-08-29T08:49:43.559712+00:00, sha 38a104a27822)
  - site_page: https://docs.falkordb.com/ (fetched 2026-08-29T08:49:43.562481+00:00, sha 3e8ac7f7ff94)
  - site_page: https://www.falkordb.com/plans (fetched 2026-08-29T08:49:43.564347+00:00, sha ade2e6a83f02)
  - site_page: https://www.falkordb.com/company (fetched 2026-08-29T08:49:43.565961+00:00, sha b3c1bdc4d2f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.