Skip to content

Your First Graph

Once CodeGraph is installed, building and exploring a graph takes a few commands.

Terminal window
cd your-project
codegraph init

codegraph init creates the .codegraph/ directory and builds the full graph in the same step — one command, done. From there a native file watcher keeps the index in sync on every change, so you rarely need to rebuild by hand. When you do want to:

Terminal window
codegraph index # full re-index
codegraph sync # incremental update of changed files
Terminal window
codegraph status

This reports the node/edge/file counts, the active SQLite backend, and the journal mode — a quick health check that the index is ready.

Reach for codegraph explore first — a natural-language question or a bag of symbol names returns the relevant source plus the call paths between those symbols in a single shot (the same output the codegraph_explore tool gives your agent):

Terminal window
codegraph explore "how does login work"
codegraph explore "who calls handleRequest?"

A question about one symbol, like the second, gets that symbol’s source and every line that uses it, each with the function it sits in.

For narrower, scriptable lookups there are focused commands:

Terminal window
codegraph query UserService # find symbols by name
codegraph callers handleRequest # what calls a function
codegraph callees handleRequest # what a function calls
codegraph impact AuthMiddleware # what a change would affect

These four each accept --json for machine-readable output. See the full CLI reference.

With a .codegraph/ directory present and an agent configured (see Installation), your agent uses the MCP tools automatically — no extra step.