Buildermark
Measure how much of your code is AI-generated
Visit buildermark.dev ↗What is Buildermark?
Buildermark is a local-first tool that tracks AI code generation by matching agent conversation logs with git commits. It automatically imports chat history from Claude Code, Codex, Gemini, and Cursor, then uses formatting-agnostic matching to attribute every line of code to either human or AI authorship. No workflow changes or agent hooks required.
Designed for developers and teams wanting visibility into their AI-assisted coding, Buildermark runs entirely on localhost with zero telemetry or cloud dependencies. It offers agent benchmarking to compare performance across different tools, manual conversation ratings, and native notifications showing attribution percentages at commit time. The maker built it with Claude Code and reports it generated 94% of the codebase across 364 agent conversations.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Buildermark automatically. Evidence: HN post: "it ended up being 364 agent conversations writing 94% of the code". View source.
Similar vibe-coded apps
Prescriptive methodology and agent skills for spec-driven development with AI
Shared persistent memory for AI coding tools across sessions and applications
Local context engine that prepares task-focused file packs for AI coding agents
Open-source AI job search agent that runs locally in your CLI
IDE to orchestrate multiple coding agents in one workspace
AI-native engineering philosophy and plugin for coding agents