Understand the boundary.

CodeVetter is an execution-backed verification and evaluation system for coding agents. It connects a requested task and exact agent change to executable checks, retained evidence, explicit limitations, and a pass, fail, or unverified verdict.

It is for engineers and teams evaluating or supervising coding-agent changes who need reproducible acceptance evidence before they trust, compare, or ship an agent result.

Review is one input, not the authority. A model can identify suspicious code and suggest what to test, but CodeVetter treats task-relevant execution evidence as the verdict boundary.

No hosted CodeVetter verification backend is required. Product state and execution evidence stay local. If you start an optional provider-backed review, selected prompt and code context go directly to the provider you configured under its policy.

Local checks, stored evidence, and the desktop viewer can operate without a CodeVetter service. Any review that calls Anthropic, OpenAI, or OpenRouter still requires network access to that provider.

Only the declared task and evidence boundary. A pass does not prove behavior that was never checked, and missing or irrelevant evidence must remain unverified instead of being converted into confidence.

The current public GitHub release contains an Apple-silicon macOS DMG and updater archive. The source is available under the ISC license. Other platform installers and a Homebrew cask are not currently published.

It publishes 27 synthetic cases and 29 labeled expected findings with the inputs, outputs, scorer, and limitations. It measures a bounded recognition task, not production-wide accuracy or customer adoption.