Buildermark
I made Buildermark to see exactly how much of my code is generated by my coding agents vs what I was writing by hand. For this project, it ended up being 364 agent conversations writing 94% of the code. Browse all of those here: https://demo.buildermark.dev/ It matches edits by your coding agents (scans history in `~/.claude`, '`/.codex', etc.) with git commit diffs. It does formatting-agnostic matching to be robust against auto-formatting and reorganizing code. It's open source and local only, not even any analytics. Everything is automatic... just run the app, open…
Buildermark launched on April 11, 2026 with 93 votes, #463 of 21,248 launches that month and more than 95% of that year's launches.
In plain words
Buildermark is a tool that measures how much code in a project was written by AI coding agents versus by hand. It automatically scans chat histories from Claude, Codex, Gemini, and Cursor, then matches them against git commit diffs to attribute each line of code. The matching is formatting-agnostic to account for auto-formatting and code reorganization. Buildermark runs locally on macOS, Windows, and Linux with no analytics or workflow changes required. It's open source and works automatically after selecting a project to import.
written from the facts on this page · September 2026
From the sources
Measure how much of your code is AI-generated. Buildermark matches your coding agent diffs with commits to calculate how much is by agents. Open source. Runs natively on macOS, Windows, and Linux.
Measure how much of your code is AI-generated. Open source and local-first.
Buildermark matches your coding agent logs with git commits to attribute every line — local and open source . No workflow changes. No agent hooks. Track the exact percentage of each commit that was written by an AI coding agent — no reliance on agent hooks, no manual tagging. Rate agent conversations manually, or let the agent log its own critique with the /rate-buildermark skill. Compare how Claude, Codex, Gemini, and Cursor perform on your actual codebase. Chat history from Claude Code, Codex, Gemini, and friends is imported automatically. Add shared folder paths to pull from VMs and containers. Your git history loads automatically. Nothing leaves your machine. A formatting-agnostic…from buildermark.dev
In the maker’s words, at launch
I made Buildermark to see exactly how much of my code is generated by my coding agents vs what I was writing by hand. For this project, it ended up being 364 agent conversations writing 94% of the code. Browse all of those here: https://demo.buildermark.dev/ It matches edits by your coding agents…
Does a similar job
all alternatives →
AI Code Detector – detect AI-generated code with 95% accuracy2025 · code-detector.ai · ▲72Hey HN, I’m Henry, cofounder and CTO at Span (https://span.app/). Today we’re launching AI Code Detector, an AI code detection tool you can try in your browser. The explosion of AI generated code has created some weird problems for engineering orgs. Tools like Cursor and Copilot are used by virtually every org on the planet – but each codegen tool has its own idiosyncratic way of reporting usage. Some don’t report usage at all. Our view is that token spend will start competing with payroll spend as AI becomes more deeply ingrained in how we build software, so understanding how…
Weave2025 · app.workweave.ai · ▲237Hey HN, We’re building Weave: an ML-powered tool to measure engineering output, that actually understands engineering output! Why? Here’s the thing: almost every eng leader already measures output - either openly or behind closed doors. But they rely on metrics like lines of code (correlation with effort: ~0.3), number of PRs, or story points (slightly better at ~0.35). These metrics are, frankly, terrible proxies for productivity. We’ve developed a custom model that analyzes code and its impact directly, with a far better 0.94 correlation. The result? A standardized engineering output…
PlannotatorApr 2026 · github.com · ▲97I started this in January as a hook for Claude Code's plan mode: when it finished planning, instead of approving a wall of text in the terminal, the plan opens in your browser and you could mark it up like a document. Your annotations go back into the agent session. It grew from there. There's now PR-style code review (git, jj, p4, GitHub/GitLab PRs) and annotation for markdown, URLs, and folders. Agents produce a lot of HTML now, so Plannotator renders those artifacts and lets you annotate them too. Nine harnesses are supported: Claude Code, Codex, Copilot CLI, Gemini, OpenCode, Kiro,…
Questions this answers
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app