EdgeQuake

Apache-2.0 GraphRAG engine in Rust, runs on local models

AI Agents / GraphRAG · Apache-2.0 · 2.3k

Reviewed 2026-10-14 · last push 2026-10-18 · repo checked 2026-10-19

What's Good

Apache-2.0 (raphaelmansuy/edgequake), release v0.35.0. A setup wizard detects local model servers — Ollama, LM Studio, MLX or llama.cpp — so it can run fully on your own machine with no API key; OpenAI or Anthropic keys are optional for faster results. Binds to localhost by default. ★~2.2k.

The Catch

Pre-1.0 with a small group of contributors (about a dozen), so expect breaking changes. Graph quality depends heavily on the model you use for entity extraction — small local models produce thinner, noisier graphs, and the first local run pulls several GB of models. Vs cognee (a more established memory and knowledge-graph layer for agents): EdgeQuake is the lighter Rust option for local GraphRAG.

Verdict

Local-first GraphRAG in Rust — worth a try for private documents, if you can give it a capable extraction model.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/edgequake.svg)](https://stackgems.com/gems/edgequake)

HTML

<a href="https://stackgems.com/gems/edgequake"><img src="https://stackgems.com/badge/edgequake.svg" alt="EdgeQuake reviewed on Stack Gems" height="20"></a>

AI Agents →

Related