CodeLean AI Code Audit

Measure and reduce the excess code AI agents pile into your repo

Problem

Existing benchmarks measure solve rate and token cost but do not punish excess code, which makes a codebase harder to maintain long term. One Show HN explicitly created an open-source benchmark to count how many coding units AI models add, showing this is now taken seriously.

Solution

Connect to repo history, quantify the syntax units, duplicate patterns, and mergeable logic added by each AI commit, then surface slimming suggestions and a lean score. Developers can see at a glance which agent is bloating the codebase.

Users

Developers and tech leads maintaining the same repo with AI agents long term, plus open-source maintainers who care about code health.

MVP

Parse git history and patches; count statement and expression unit deltas; detect duplicate and near-duplicate logic; output a repo lean score and weekly waste ranking; generate a one-click slimming report.

Revenue

Open-source core; hosted tier priced per repo; enterprise tier with team dashboards and CI integration.

Why now

AI-generated code is now the default workflow, but nobody owns long-term maintainability; this niche metric was just proposed, so an indie dev can be first to build the tool.