CodeGraph

What It Is (confidence: low)

CodeGraph (colbymchenry/codegraph) is a repo-navigation tool for AI coding agents: it builds a local map of a codebase — symbols, what calls what, and how files depend on each other — so the agent can ask once and get the right code back instead of grepping around and opening files one by one.

Claims (confidence: low)

• Benchmark: 58% fewer tool calls, 22% faster, and file reads cut to almost zero across 7 repos.
• Savings depend on repo size and usage volume: barely noticeable on small repos; much more interesting on large codebases with frequent agent runs.

Relationship to Other Tools (confidence: medium)

CodeGraph addresses the same input-waste problem class as tool-search-tool and code-mode-orchestration but from the navigation side: instead of deferring or scripting tool access, it makes repo navigation a single graph query. It is conceptually adjacent to the vault’s codebase-memory (tree-sitter knowledge-graph memory over MCP) — both replace grep-plus-open with graph-backed lookup. Where rtk-rust-token-killer compresses terminal output and headroom compresses arbitrary context, CodeGraph cuts the number of retrieval actions the agent takes.

Implications

For large-codebase agent workflows, repo-navigation maps are a distinct token lever: they reduce tool calls and file reads (the repetitive-grep waste documented in token-usage-reduction) rather than compressing bytes. The 7-repo benchmark is vendor-reported, so treat the numbers as direction, not guarantee.

Open Questions

• Whether CodeGraph’s map stays fresh as the repo changes (staleness cost vs. grep).
• Whether the 58%/22% figures replicate independently across repo sizes.

Related

tool-search-tool — definition deferral, the query-side cousin of graph navigation code-mode-orchestration — gateway-side scripting of tool calls codebase-memory — tree-sitter graph memory over MCP, adjacent mechanism token-usage-reduction — the cost-lever space this tool operates in rtk-rust-token-killer — different waste source (terminal output), same family

Sources

• raw/prompts/articles/reduce-wasted-tokens.md