About

CodeVetter is an execution-backed verification and evaluation system for coding agents. It determines whether an agent completed a software task correctly using reproducible runtime evidence — not another LLM opinion. The review pipeline runs locally in a Tauri desktop app; your repository never hits a CodeVetter server.

What it does

The core loop is: task → agent change → executable verification → evidence → measurable verdict. CodeVetter runs tests, type checks, builds, and profiling against the agent's diff, then produces a portable evidence bundle that proves whether the task is done.

Open source

CodeVetter is open-source under the ISC license. The source lives atgithub.com/Codevetter/codevetter. The current Apple-silicon macOS build is published through GitHub Releases with an updater archive.

Built by

Sarthak Agrawal — AI infrastructure and product engineer. More atsarthakagrawal.dev.

Public benchmark

CodeVetter maintains apublic benchmarkof reproducible verification cases, a scorer, and published results with documented limitations.