One map of the code
One graph across every repository and team, built once and kept current. Nobody re-learns the codebase by hand, and what one engagement learns carries into the next.
Backed by
Y Combinator
Y CombinatorThe knowledge graphcontrol plane forenterprise software.
Free plan, no card · run the open-source engine yourself
116,702Github stars
6.7MPyPI downloads
13.1MRepositories indexed
How it works
Answers with proof
Every answer is a path through the graph you can open, spanning code, docs, wikis and contracts. Evidence rather than opinion, for audited and regulated work.
See what breaks
Before the merge, the graph follows every edge to what a change breaks. The agent reads the graph instead of the repo, so the token bill buys answers.
Used by engineers at
Features
Structure your assistant can walk.
One run maps the repo. Here’s what you get to work with.
Interactive graph
The graph maps your repo into communities, god nodes, and click-to-inspect symbols.
Fully on-device
Run the open-source engine and parsing stays on your machine: 36 tree-sitter grammars, no uploads, no telemetry.
Query, don’t grep
Your assistant follows real paths with query, path, and explain, not re-reads.
17 assistants
Your assistant queries the graph over MCP, in Claude Code, Cursor, Copilot, and 14 more.
Cross-repo graph
One persistent graph across every repo, so answers follow owners across services.
PR review
graphify prs triages CI, review, and merge-conflict risk, learning from each merge.
Formal verification
Enterprise checks verify every change at the merge gate with graph-aware review.
Side by side
Graph, chunks or grep.
Four tools an enterprise shortlists. Here’s what each one can actually do.
Graphify| Capability | Graphify |  CodeRabbit |  Greptile |  Sourcegraph |
|---|---|---|---|---|
 Differential verification | prove it or break it | review only | review only | search only |
 Cross-repo blast radius | every dependent repo | per-PR guess | single repo | refs, no verdict |
 Typed code graph | persistent, queryable | per PR, ephemeral | untyped AST | cross-repo (SCIP) |
 Multi-hop reasoning | native traversal | per PR only | agentic hops | agentic retrieval |
 Auditable answer | a path you can open | inline comments | file + line | symbol snippets |
 Provenance | every edge tagged | per finding | per finding | code-nav refs |
 Deployment | SaaS · BYOC · air-gap | self-host, 500+ seats | self-host / air-gap | self-host (enterprise) |
 Any AI assistant | any MCP client | own bot + MCP client | MCP server + API | OpenCtx / MCP |
 License | open core (Apache 2.0) | proprietary | proprietary | proprietary |
As each vendor documents it, September 2026. CodeRabbit and Greptile review pull requests and Sourcegraph searches code; the rows are what enterprise teams asked us for, not the whole of any product.
Trust
Run it on your machine, or let us run it.
The open-source tool never sends your code anywhere. The hosted product is a choice, not the only way in.
On-device
The command-line tool parses locally on 36 tree-sitter grammars and writes the graph to a file on your own disk.
No telemetry
The tool sends no usage pings, no crash reports and no analytics. Nothing to opt out of, because nothing is sent.
Apache 2.0
The whole source is Apache 2.0 on GitHub. You need not trust this page; read what the code does.
Yours to host
Serve the graph over stdio or over HTTP on infrastructure you own, and on Enterprise run the whole thing there.
Proof
- 79× fewer tokens
After a weekend of using it on MemMachine, I’m not going back. We’re seeing 79x token reductions, and zero vector database needed.
Steve Scargall, MemVergeSenior Product Manager & Software Architect - 71.5× fewer tokens
Instead of Claude Code re-reading every file, it queries the graph — which is persistent across sessions and costs a fraction of the tokens.
lucasrosatiObsidian + Graphify setup, measured per session - Rootly integration
The data already lives in Rootly. The graph makes the structure visible.
Sylvain Kalache, RootlyHead of AI Labs · on Rootly’s own Graphify plugin - Fewer blind searches
Instead of Claude blindly searching through files, Graphify helps it understand relationships, dependencies and affected areas first. Less blind searching. Better context. Smarter implementation.
Audran Yematha@WolfhardsA - A second brain for code
It takes the best of the wiki index and graphs, but helps you more with code without leaving any document or md file behind — it eats everything and still works like a 2nd brain.
TheSaid@sineidesis
FAQ
Frequently Asked Questions
Common questions about how Graphify works.
RAG splits your code into chunks, embeds them, and retrieves the top-k that look similar to your question. Graphify builds a real graph and traverses it, so every answer is an explicit path with file:line citations. There are no embeddings and no vector store. You follow the actual call and import edges instead of guessing which chunks are relevant.
That is your choice. The open-source engine parses code locally with tree-sitter, which is deterministic AST extraction with no model call and no telemetry, so nothing leaves your machine unless you point the non-code pass at a hosted model. The hosted product builds and keeps the same graph for you in the cloud, on the repositories you connect.
Yes. The hosted product at app.graphify.com has a Free plan with no card, and Pro and Teams by seat above it (those need a card). The open-source engine is free under Apache 2.0, runs on your own machine, and needs no account. Teams can also self-host the early-access enterprise layer, which adds merge-gate verification and graph-aware review.
17, including Claude Code, Cursor, Copilot, Codex, Gemini CLI and Aider. Running graphify install registers the /graphify skill with the assistants it detects, and the graph is also served over an MCP server any client can query.
LSP answers one hop: where a symbol is defined, where it is referenced. A graph answers questions that span the codebase, such as what breaks if you change this, every path between two functions, and how a doc or config connects to the code. It is persistent, queryable by your assistant, and every edge carries a provenance tag.
ctags builds a flat symbol index for jump-to-definition. Sourcegraph is hosted code search you send your code to. Graphify parses on-device and produces a typed graph your assistant traverses over CLI or MCP. It is not a symbol table and not a search box.
Yes, incrementally. A code change re-parses only the changed file through the local AST pass, with no re-embedding and no full re-index. Install the git hook and the graph rebuilds on every commit.
Yes. Code parsing is always local. Point the semantic pass at a local model such as Ollama, or any OpenAI-compatible server like vLLM, and nothing leaves the machine: tree-sitter on code, your local model on docs.
It can store embeddings as one signal on a node, but retrieval is a graph traversal rather than a similarity search. Results come back connected and explainable instead of as a ranked list of lookalike chunks.