A repo investigator for Claude Code and Codex.

RepoTracer has a separate agent investigate the repo and report back to Claude Code or Codex.

Up to 2.7× as much work from the same limits · up to 25% faster
When the outputs of the two runs differed in quality, RepoTracer produced the better result.
_{Same task, model, repo, and timeout. RepoTracer usage included. See every run.}

Claude Code · Codex · MCP · MIT

Demo · Benchmarks · Install · Architecture · Website

_{Same task · same model · same repo · same timeout · RepoTracer investigator usage included}

npx repotracer@latest setup

Without RepoTracer, every search and file read stays in the same conversation and counts against the same limits the coding agent later uses to implement the change.

With RepoTracer, RepoTracer runs the investigation in a separate conversation and reports back to the coding agent.

On the current complete-task benchmarks, the same limits covered 1.38× to 2.68× as much work. When the outputs of the two runs differed in quality, RepoTracer produced the better result.

A complete run that costs 62.68% less lets the same fixed limit cover 2.68× as many runs.

without RepoTracer = coding-agent usage
with RepoTracer    = coding-agent usage + investigator usage

We only call it a saving if the whole run costs less and still passes the task's quality check.

Raw runs, grading, and checksums are public.

Full benchmark writeup →
Raw benchmark artifacts →
Why complete-task measurement matters →

• Trace behavior across files and related repos
• Follow definitions, references, callers, and execution paths
• Run checks or experiments to test a theory
• Continue a previous investigation instead of starting over
• Report what it could not resolve and what it already checked
• Run independent investigations in parallel

"Rename this variable in src/config.ts"
  → Claude Code / Codex

"Trace why refresh tokens fail after rotation"
  → RepoTracer

The router made the right call on all 42 cases in the current routing test.

Install it once. Prompt normally.

Choose Claude Code, Codex, or both.

RepoTracer uses the native CLI you are already signed into. No second provider login or gateway account is required.

Integration details →

Use any OpenAI-compatible endpoint, including Ollama or vLLM.

npx repotracer@latest setup \
  --base-url http://localhost:11434/v1 \
  --model deepseek-coder

npx repotracer@latest setup

Choose Claude Code, Codex, or both, then accept the defaults or pick your investigator.

Run the same command later to reconfigure or uninstall.

Want the CLI in your shell too?

npm install -g repotracer
# or
cargo install --git https://github.com/repotracer/repotracer --locked repotracer

RepoTracer is a Rust MCP server. Native investigations run through the Claude Code or Codex CLI you already use. For OpenAI-compatible models, RepoTracer provides the repo tools and drives the investigation itself.

Full architecture →

repotracer "where is authentication handled?"
repotracer scout "trace refresh rotation"
repotracer symbols "Config" --mode references
repotracer serve
repotracer doctor
repotracer status
repotracer settings
repotracer update
repotracer uninstall --yes

git clone https://github.com/repotracer/repotracer
cd repotracer
cargo test --workspace
cargo run -p repotracer -- doctor
cargo run -p repotracer -- scout "where is config loaded?" --mock

CI runs without a GPU, local model runtime, or API key. Live native-CLI smoke tests are documented in CONTRIBUTING.md.

• Website
• Benchmarks
• Architecture
• Security
• Claude Code and Codex integration
• Contributing
• Microsoft FastContext paper

RepoTracer is an independent project inspired by FastContext. It is not affiliated with or endorsed by Microsoft. See NOTICE.

MIT. See LICENSE and NOTICE.