AI coding agents explore unfamiliar repositories with grep and file reads, which costs many turns and tokens. Large codebases hide the relationships between functions (who calls what, what depends on what) that agents need to answer architecture and impact questions.
See our solution in action.
The problem we set out to solve
As codebases grow, finding the right code becomes increasingly time-consuming. Developers and AI coding assistants struggle to see how different components connect, making code exploration harder and increasing the risk of missed dependencies and unexpected bugs.
From problem to possibility
Meet GraphRelay - a smarter way to navigate complex codebases. It helps developers and AI coding assistants find relevant code and uncover hidden connections, reducing manual searching and enabling faster, more confident code changes.
Key Feature & Modules
Search code finds code from a natural-language description
Search code finds code from a natural-language description or finds implementations of a named interface. Lexical BM25 plus graph expansion surfaces related callers and callees, so the agent needs fewer exploratory searches.
Inspect returns a symbol's definition
Inspect returns a symbol's definition, callers and callees, or the contents and summary of a file or module. It can return full source in place of a separate file read.
Keep trace impact in mind
Trace impact shows what depends on a symbol before it is changed, reducing the risk of breaking callers in other files.
Keep file watcher updated
A file watcher keeps the index fresh as files change, and watch status reports indexing progress and health, so results stay trustworthy while editing.
Result
Query → FTS5 BM25 lexical search → 1-hop graph expansion → personalized PageRank → enrich → rerank (graph + keyword) → ranked results
