Buildermark - Measure your AI-generated code
How much of your code is written by agents?<br>Buildermark matches your coding agent logs with git commits to attribute every line — local and open source .<br>No workflow changes. No agent hooks.
Downloads<br>Try the live demo
What it does<br>A measurement layer for coding agents.
Agent attribution<br>Track the exact percentage of each commit that was written by an AI coding agent — no<br>reliance on agent hooks, no manual tagging.
Conversation ratings<br>Rate agent conversations manually, or let the agent log its own critique with the /rate-buildermark skill.
Agent benchmarking<br>Compare how Claude, Codex, Gemini, and Cursor perform on your actual codebase.
Supported agents<br>Every agent you use.<br>Claude Code CLI<br>Claude Code Cloud<br>Codex CLI<br>Codex Cloud<br>Gemini CLI<br>Cursor<br>Missing one? File a request →
Local-first<br>Your data never leaves<br>your machine.<br>✓Zero analytics, zero telemetry<br>✓Runs entirely on localhost:55022<br>✓MIT licensed, audit-friendly<br>✓Only outbound request: checking for updates
How it works<br>Fully Automatic
01<br>Auto-import conversations<br>Chat history from Claude Code, Codex, Gemini, and friends is imported automatically. Add<br>shared folder paths to pull from VMs and containers.
02<br>Auto-import commits<br>Your git history loads automatically. Nothing leaves your machine.
03<br>Auto-match diffs<br>A formatting-agnostic matcher aligns conversation diffs to commit diffs — robust against<br>auto-formatters, reorderings, and line-ending noise.
Native notifications<br>Attribution in your notification center, the moment you commit.<br>See agent percentage for each commit immediately — no dashboard required. Works across<br>macOS, Windows, and Linux.
Desktop apps<br>macOS 15+<br>Windows 10+<br>Linux CLI
Browser extensions<br>Chrome<br>Firefox<br>Safari<br>For importing from cloud-based agents
Architecture<br>A local app container runs a Go server on localhost that serves the web UI. No cloud.<br>No accounts. No sync.
Coming soon<br>Team Server.<br>Aggregate. Compare. Compete.<br>A self-hosted server that rolls Buildermark metrics up across your whole org. See who's<br>shipping with agents, which projects adopt fastest, and how your dev process is changing —<br>all on your own infrastructure.<br>Join the waitlist →