Buildermark: Measure how much of your code is written by agents

Buildermark, a new open-source tool, measures the percentage of code written by AI coding agents by matching agent logs with git commits. It supports multiple agents like Claude, Codex, Gemini, and Cursor, runs locally without sending data externally, and offers team aggregation features. The tool aims to provide transparency and benchmarking for AI-assisted development.

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