Grep finds text. It doesn't find reasons.
Agents read a codebase the way you'd read a phone book: one file at a time, matching strings, hoping the answer is nearby. Two hundred hits for "login", and none of them say why it fails on Tuesdays.
Turn the repo into a graph. On this machine.
Parsing, symbol resolution, call edges and framework wiring — deterministic and CPU-bound. No model, no upload, no minimum spec. The graph is written beside the repo and updates as files change.
Follow the call, not the keyword.
"Why is login failing intermittently?" becomes a walk through real edges: router, handler, token check, the write that isn't ordered against the read. The answer cites lines, because it came from them.
See the blast radius before the diff.
Change a signature and CodeMarrow resolves everything that reaches it — callers of callers, and the middleware and wrappers around them. Your agent plans the whole change instead of discovering it in CI.
One map. Every agent reads it.
The same tools the app uses are served over MCP, read-only. Claude Code, Codex or any MCP client gets structure instead of search — with one line of setup.
