Your first knowledge graph

On this page

Graphify turns a repository into a graph of its functions, classes, imports, and relationships. Your assistant can query that graph instead of repeatedly scanning the same files. This quickstart uses the open-source engine on your machine. You need Python 3.10 or later and a supported coding assistant. For the hosted product, see Graphify Cloud.

Install the CLI

uv tool install graphifyy
graphify --version

graphify --version prints the version you installed. The latest release is on PyPI and in the changelog. The package is graphifyy, with two y’s. The command is graphify. You can also use pipx install graphifyy.

Connect your assistant

graphify install

This installs the Graphify skill for a detected assistant. To choose one explicitly:

graphify install --platform cursor

See all integrations for your assistant’s setup.

Map a repository

Open a repository in your assistant, then enter this in its chat:

/graphify .

In Codex, select the Graphify skill with $graphify and ask it to map the current repository. This is an assistant instruction, not a shell command.Code is parsed locally. If the repository includes documents or media, the skill can use your assistant’s model for semantic extraction. For an explicit code-only run, use the local CLI workflow.

Inspect the output

graphify-out/
├── graph.html        Interactive graph
├── GRAPH_REPORT.md   Concepts, communities, and suggested questions
└── graph.json        The graph used by CLI and MCP queries

Open graph.html in your browser. Click a node to inspect its connections, or start with the report for a tour of the architecture.

Ask a question

From a terminal at the repository root:

graphify query "how does authentication reach the database?"

Use names from your graph to investigate further:

graphify explain "YourService"
graphify path "YourService" "YourRepository"

The names above are placeholders. A path only exists if those nodes and connecting edges exist in your project.

Take the full tutorial

Build a small example and follow a real relationship.

Give your agent MCP tools

Expose the graph as structured tools in your editor.