Graphify

Open-source on-device knowledge graph engine that turns code, docs, papers, meetings and images into a queryable graph.

Free· MIT-licensed, free forever; cloud tier hinted but unpriced (waitlist)RAGMulti-model

Best for

Pick Graphify if you want a local-first, open-source knowledge graph over your own code, docs and meetings instead of yet another cloud RAG service.

Skip if

Skip it if you need a production-ready product today or a managed hosted RAG API with SLAs.

Graphify is an MIT-licensed knowledge graph engine that ingests heterogeneous inputs — source code (with AST awareness), markdown docs, PDFs and papers, meeting transcripts, browser history, even images and diagrams — and decodes them into a single traversable graph. The pitch is 'any input, one graph, complete recall': instead of throwing everything into a vector store and praying for retrieval, it builds explicit nodes and edges that you can walk to surface relationships like 'this RFC ↔ this commit ↔ this meeting decision'. It runs on-device by default with an optional cloud mode.

The differentiator versus generic RAG stacks is the incremental graph maintenance and the local-first posture: when a file changes, only affected nodes and edges update, so the corpus stays coherent at millions of files without re-embedding everything. That makes it interesting for engineers and researchers who want long-horizon memory over a private corpus rather than a chatbot wrapper. As of this writing the project is in waitlist / early-access; the marketing copy leans heavily on MIT licensing and 'free forever' framing, so expect a community-driven OSS release with cloud add-ons later rather than a polished SaaS today.

Editor's take

Promising positioning — on-device, MIT, graph-native — and exactly the kind of project the RAG space needs more of. But it's still a waitlist landing page with bold claims and thin technical disclosure, so treat it as one to watch rather than one to deploy. Worth bookmarking until the repo and docs land.

— The AI Tool Bible editorial team

Pros

✅ MIT-licensed and runs fully on-device — no data leaves your machine
✅ Incremental updates: only changed nodes/edges re-process, scales to millions of files
✅ Ingests broad input set: code/AST, docs, papers, meetings, browser history, images
✅ Explicit graph beats opaque vector retrieval for traceable, multi-hop questions