Skip to content
116.8k
Log inGet started
What is Graphify

A map ofyour own code.

The knowledge graph your assistant queries instead of grepping. Start free at app.graphify.com, or run the open-source engine yourself.

How it works

Connect a repo.

Connect a repository at app.graphify.com. Graphify builds its graph and keeps it current, ready for your assistant to query over MCP.

  • Connect your repo

    Point Graphify at a repository at app.graphify.com.

  • It builds the graph

    Built for you, then reindexed on every push so it stays current.

  • Your assistant queries it

    Over MCP, so answers come back as paths, not file dumps.

Asking it

Answers carry their route.

A question in plain English, a path back, with a file and line on every hop.

$ graphify query "what connects auth to the database?"

AuthService -> SessionStore -> DatabasePool      [EXTRACTED]
  src/auth/service.py:42 -> src/db/pool.py:17

The arrow is not a guess. Each hop is an edge that was read out of the source, and each one comes back with the file and the line it was read from, so an answer can be opened rather than believed. The tag on the end says how it was arrived at.

Open source

Or run it yourself.

The engine is free and open source under Apache 2.0. Install it and build the graph on your own machine, with no account.

$ uv tool install graphifyy
  installed graphify

$ graphify install
  /graphify skill registered with Claude Code

# then, inside your assistant:
/graphify .

  graphify-out/graph.html        interactive graph
  graphify-out/GRAPH_REPORT.md   architecture report
  graphify-out/graph.json        machine-readable graph
Boundaries

What it is not.

Three things it gets mistaken for.

  • Not RAG

    No embeddings, no similarity search. An answer is a path with file and line, not chunks that looked close.

  • Yours to run

    The open-source engine runs on your machine and writes plain files into your repository, with no account. The hosted product runs the same graph for you when you would rather not.

  • Not an agent

    It writes no code and takes no actions. It is a map your assistant reads before it edits, so what it does next can be cited.

Honesty

Where it stops.

The edges worth knowing before you install it.

  • Inferred edges are guesses

    Static extraction cannot see dynamic dispatch, reflection or wiring in config. Those edges are kept and tagged.

  • A graph reflects a point in time

    It reindexes on every push, so it stays current on its own.

  • Depth needs a model

    The structural graph is pure syntax and needs no key. The richer passes run through the assistant session you already have.

FAQ

Common questions

The short answers.

  • A knowledge graph of your codebase that your AI assistant queries instead of grepping, parsed with tree-sitter. Use it hosted at app.graphify.com, or run the open-source engine yourself.

  • 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 machine, and needs no account.

  • With the open-source engine, no: parsing runs on-device and the graph is written to local files in graphify-out, with no telemetry. The hosted product builds and keeps the same graph for you on the repositories you connect.

  • 17, including Claude Code, Cursor, Codex, Gemini CLI, Copilot, Aider, Amp and Devin. graphify install registers the ones it detects, and the graph is also served over MCP.

Try Graphify now.

Try for free