EdgeQuake v0.34.0 — Graph-RAG in Rust
One binary. One Postgres. Any LLM, cloud or fully local.
Vector search finds similar text. It struggles when the answer lives in the relationships between things:
"Which contract affects which product?"
"Who reports to whom?"
"What themes run across these 200 papers?"
EdgeQuake implements LightRAG's Hybrid GraphRAG in Rust. Documents become a knowledge graph of entities and relationships. At query time, vector search and graph traversal work together, and every answer comes with its sources.
🏢 Built for the enterprise
- One datastore: PostgreSQL 16/17/18 with pgvector and Apache AGE. No separate vector or graph DB
- Multi-tenant, fail-closed workspace isolation
- SSO with Keycloak/OIDC, built-in auth and audit logging
- Provider keys encrypted at rest (AES-256-GCM), write-only
- Safe upgrades: the API never migrates your DB. Migrations are explicit and replay-tested from every release
- edgequake doctor checks DB, schema, roles and security posture
- PDF vision pipeline for tables, scans and complex layouts
🔌 Pick your LLM, per role
OpenAI, Anthropic, Gemini, Mistral, or private on your own machine with Ollama, LM Studio, MLX or llama.cpp. Each workspace can assign a different model to extraction, query, summary, embedding and vision.
- The Second Brain: EdgeQuake MCP
The MCP server plugs your knowledge graph into Claude Desktop, Cursor, VS Code or any MCP client. Your agents can:
- Remember: push notes, text and PDFs into the graph
🔎 Recall: multi-hop answers in hybrid mode, with sources
🕸️ Explore: entities, neighbours and relationships
🗂️ Organize: one workspace per project, team or client
Workspace-scoped API keys keep each agent on least privilege. Memory persists across conversations and stays on your infrastructure.
📊 Honest numbers (GraphRAG-Bench, n=200, same corpus and models)
• Accuracy: 0.792 vs 0.786 for LightRAG, a statistical tie
• Warm query p50: 82 ms vs 993 ms
• Evidence recall: LightRAG ahead (0.949 vs 0.932)
The pitch is the same retrieval quality, productionised. We publish where we tie and where we lose.
🚀 Try it, Docker only:
curl -fsSL https://lnkd.in/g8a6a4Ee | sh
2.1k ⭐, 99 releases, 14 contributors. Thank you all.
EdgeQuake is a real open-source GraphRAG framework written in Rust. Its official repository documents a hybrid retrieval architecture that combines vector search with knowledge-graph traversal, using PostgreSQL with pgvector and Apache AGE. It also documents Docker deployment, multiple LLM integrations, workspace isolation, authentication features and MCP integration for AI agents.
The published benchmark reports accuracy of 0.792 for EdgeQuake and 0.786 for LightRAG on a 200-question GraphRAG-Bench evaluation. The project's documentation characterizes this as a statistical tie, not a demonstrated accuracy win. Evidence recall favors LightRAG at 0.949 versus EdgeQuake at 0.932.
The latency comparison requires particular care. The reported 82 ms versus 993 ms result is for warm queries with LLM and embedding caches, not a general cold-query performance comparison. In the documented cold-query test, median latency is approximately 4,447 ms for EdgeQuake and 4,359 ms for LightRAG, making their performance broadly comparable under that test. Therefore, the headline speed advantage should not be generalized to uncached queries.