# CodeVetter

> Execution-backed verification for coding-agent changes, with local checks, portable evidence, explicit limitations, and a measurable verdict.

Use CodeVetter to verify coding-agent changes with executable tests, portable evidence and an explicit verdict. Run locally; do not upload private repositories to a CodeVetter server.
The macOS distribution packages the local CLI and stdio MCP sidecar. There is no separately published codevetter npm package or hosted MCP/verification endpoint.
- [AI catalog](https://codevetter.com/.well-known/ai-catalog.json)
- [Agent skills index](https://codevetter.com/.well-known/agent-skills/index.json)
- [Local verification skill](https://codevetter.com/.well-known/agent-skills/codevetter-local-verification/SKILL.md)
- [Pricing and availability](https://codevetter.com/pricing.md)

<!-- Keep in sync with robots.txt and ai.txt. -->

## Public pages

- [CodeVetter](https://codevetter.com/index.md): Verify whether a coding agent completed its task. CodeVetter binds the exact change to executable checks, evidence, limitations, and a measurable verdict.
- [About CodeVetter](https://codevetter.com/about.md): CodeVetter is an execution-backed verification system for coding agents. Local-first, open-source, and built by Sarthak Agrawal.
- [Download CodeVetter](https://codevetter.com/download.md): Download the current Apple-silicon macOS release of CodeVetter from GitHub Releases, or inspect and build the open-source repository.
- [CodeVetter FAQ](https://codevetter.com/faq.md): Clear answers about CodeVetter's execution-backed agent verification, local evidence, provider boundary, benchmark, and current macOS availability.
- [Comparing local desktop verification with cloud PR review](https://codevetter.com/compare.md): Compare CodeVetter, CodeRabbit, and Greptile on where your code is processed and what each publishes as reproducible evidence, sourced from each vendor's…
- [AI code review benchmark for agent-written bugs](https://codevetter.com/benchmark.md): Public AI code review benchmark for agent-written bugs: 27 cases, 29 labeled findings, catch rate, precision, downloads, and stated limitations. Reproducible.
- [CodeVetter docs](https://codevetter.com/docs.md): The local-first knowledge system for the CodeVetter repository.
- [CodeVetter changelog](https://codevetter.com/changelog.md): Verified CodeVetter product updates, written as concise user-visible outcomes.
- [CodeVetter privacy](https://codevetter.com/privacy.md): What CodeVetter stores, what it never sends to a server, and how API keys are handled.
- [CodeVetter terms of use](https://codevetter.com/terms.md): Terms of use for CodeVetter desktop software and codevetter.com. Execution-backed verification for coding-agent changes, with local checks, portable…
- [Coding-agent verification](https://codevetter.com/coding-agent-verification.md): Learn how coding-agent verification connects a task, agent change, executable checks, evidence, and a measurable verdict — and how to verify code inside the…
- [How to verify AI-generated code](https://codevetter.com/verify-ai-generated-code.md): Verify AI-generated code with a runnable Node.js failure-and-fix example, executable acceptance checks, regression checks and reproducible evidence.
- [AI code review vs. coding-agent verification](https://codevetter.com/ai-code-review-vs-verification.md): Validate AI-generated code with a runnable failure-and-fix check. Compare review with executable verification and inspect the evidence.
- [Coding-agent verification evidence bundles](https://codevetter.com/verification-evidence-bundle.md): See the identities, execution records, artifacts, uncertainty, and re-check linkage a coding-agent verification bundle should contain.
- [CodeVetter vs Greptile: local verification or repository-aware review?](https://codevetter.com/codevetter-vs-greptile.md): Compare CodeVetter's local execution-backed verification with Greptile's repository-aware AI code review and TREX execution workflow.
- [CodeVetter vs CodeRabbit: verification evidence or automated PR review?](https://codevetter.com/codevetter-vs-coderabbit.md): Compare CodeVetter's execution-backed coding-agent verification with CodeRabbit's automated PR, IDE, and CLI code review workflow.
- [CodeVetter articles](https://codevetter.com/articles.md): Editorial articles on execution-backed coding-agent verification, reproducible evidence, and verification receipts.
- [Tools that shaped CodeVetter](https://codevetter.com/inspiration.md): A detailed, source-linked ledger of the tools and ideas that shaped CodeVetter's approach to code context, agent workflows, and executable verification.
- [Agent evaluation vs tests vs code review: what each can actually prove](https://codevetter.com/articles/agent-evaluation-vs-tests-vs-code-review.md): Understand the distinct proof boundaries of agent evaluation, software testing, and static AI code review when checking agent-written software changes.
- [What an evidence receipt for a coding agent should contain](https://codevetter.com/articles/coding-agent-evidence-receipt-spec.md): Learn what a machine-readable evidence receipt for AI coding agents must contain, including identity bindings, execution records, taxonomy, and failure trails.
- [How to verify AI-generated code changes beyond code review](https://codevetter.com/articles/verifying-ai-code-changes-beyond-code-review.md): Static AI code review cannot prove software works. Learn how to bind task intent, run executable checks, and capture evidence for AI code changes.
- [Why reproducible evidence matters when an AI agent says a task is done](https://codevetter.com/articles/why-reproducible-evidence-matters-when-an-ai-agent-says-a-task-is-done.md): When an AI coding agent says a task is done, how do you verify it? Learn why reproducible execution evidence matters more than LLM-as-judge opinions.
- [AI code validation: requirements, tests, and evidence](https://codevetter.com/ai-code-validation.md): AI code validation, verification, and review are three different jobs. Learn what validating agent-generated code actually requires and how to run a…
- [Anime List optimization case study](https://codevetter.com/benchmark/optimization/anime-list.md): Anime List: A two-file import-boundary change materially reduced one local Vite navigation, while a separate production build showed almost no…
- [Free AI optimization case study](https://codevetter.com/benchmark/optimization/free-ai.md): Free AI: A one-pass model-selection loop removed an intermediate array and improved every tested registry size without growing the patch.
- [Starboard optimization case study](https://codevetter.com/benchmark/optimization/starboard.md): Starboard: A plausible incremental token scanner passed focused correctness but ran slower, so CodeVetter rejected it and restored the original code.
- [Optimization benchmarks and case studies](https://codevetter.com/benchmark/optimization.md): Dated CodeVetter optimization trials with tested flows, repeated measurements, correctness boundaries, patch cost, rejected candidates, and proof JSON.
- [CodeVetter vs open-source agent-verification CLIs](https://codevetter.com/codevetter-vs-verification-clis.md): Compare CodeVetter with open-source agent-verification CLIs like Verdict, PatchDrill, ProofGate, evigate, didrun, and verity — quoted from their own READMEs.
- [Contact CodeVetter](https://codevetter.com/contact.md): How to reach the CodeVetter team: GitHub issues, email, and social. Execution-backed verification for coding-agent changes, with local checks, portable…
- [Aider — tools that shaped CodeVetter](https://codevetter.com/inspiration/aider.md): Aider: A small, ranked repository map gives an agent useful context without dumping the whole tree. Read what CodeVetter learned and where our own…
- [Arbor — tools that shaped CodeVetter](https://codevetter.com/inspiration/arbor.md): Arbor: Deterministic graph traversal is a useful answer to structural questions. Read what CodeVetter learned and where our own implementation begins and ends.
- [ast-grep — tools that shaped CodeVetter](https://codevetter.com/inspiration/ast-grep.md): ast-grep: Structural search can express focused review rules more clearly than text matching. Read what CodeVetter learned and where our own implementation…
- [Augment Code — tools that shaped CodeVetter](https://codevetter.com/inspiration/augment-code.md): Augment Code: Fresh repository context should follow the developer across tools. Read what CodeVetter learned and where our own implementation begins and ends.
- [Bito — tools that shaped CodeVetter](https://codevetter.com/inspiration/bito.md): Bito: Repository architecture and external project context can change the meaning of a diff. Read what CodeVetter learned and where our own implementation…
- [Claude Code — tools that shaped CodeVetter](https://codevetter.com/inspiration/claude-code.md): Claude Code: An agent can discover context through targeted search and reads. Read what CodeVetter learned and where our own implementation begins and ends.
- [Cline — tools that shaped CodeVetter](https://codevetter.com/inspiration/cline.md): Cline: Planning and acting benefit from a visible boundary. Read what CodeVetter learned and where our own implementation begins and ends.
- [CodeQL — tools that shaped CodeVetter](https://codevetter.com/inspiration/codeql.md): CodeQL: Deep code queries can reveal data flow and security relationships. Read what CodeVetter learned and where our own implementation begins and ends.
- [CodeRabbit — tools that shaped CodeVetter](https://codevetter.com/inspiration/coderabbit.md): CodeRabbit: Review is more useful when it arrives in the developer’s normal change workflow. Read what CodeVetter learned and where our own implementation…
- [codesize — tools that shaped CodeVetter](https://codevetter.com/inspiration/codesize.md): codesize: A tiny heuristic can still point a reviewer toward risky code. Read what CodeVetter learned and where our own implementation begins and ends.
- [OpenAI Codex — tools that shaped CodeVetter](https://codevetter.com/inspiration/codex.md): OpenAI Codex: An agent’s patch and its execution trace should be available for inspection. Read what CodeVetter learned and where our own implementation…
- [Continue — tools that shaped CodeVetter](https://codevetter.com/inspiration/continue.md): Continue: The developer should be able to choose models and context sources. Read what CodeVetter learned and where our own implementation begins and ends.
- [Cursor — tools that shaped CodeVetter](https://codevetter.com/inspiration/cursor.md): Cursor: Codebase navigation can feel immediate inside a coding workflow. Read what CodeVetter learned and where our own implementation begins and ends.
- [DeepWiki — tools that shaped CodeVetter](https://codevetter.com/inspiration/deepwiki.md): DeepWiki: A repository can be made legible quickly through structured explanation. Read what CodeVetter learned and where our own implementation begins and…
- [DeepWork — tools that shaped CodeVetter](https://codevetter.com/inspiration/deepwork.md): DeepWork: Long agent tasks need explicit steps, artifacts, and quality gates. Read what CodeVetter learned and where our own implementation begins and ends.
- [Ellipsis — tools that shaped CodeVetter](https://codevetter.com/inspiration/ellipsis.md): Ellipsis: The useful review loop continues from finding to attempted fix. Read what CodeVetter learned and where our own implementation begins and ends.
- [Gemini CLI — tools that shaped CodeVetter](https://codevetter.com/inspiration/gemini-cli.md): Gemini CLI: A terminal agent can keep planning, tools, and code changes in one inspectable loop. Read what CodeVetter learned and where our own…
- [GitHub Copilot code review — tools that shaped CodeVetter](https://codevetter.com/inspiration/github-copilot.md): GitHub Copilot code review: A code host can make automated review a normal request on a pull request. Read what CodeVetter learned and where our own…
- [GitNexus — tools that shaped CodeVetter](https://codevetter.com/inspiration/gitnexus.md): GitNexus: A code graph can be exposed as a useful interface for agents. Read what CodeVetter learned and where our own implementation begins and ends.
- [gitoxide — tools that shaped CodeVetter](https://codevetter.com/inspiration/gitoxide.md): gitoxide: Git history can be explored through an owned Rust interface. Read what CodeVetter learned and where our own implementation begins and ends.
- [Google Code Wiki — tools that shaped CodeVetter](https://codevetter.com/inspiration/google-code-wiki.md): Google Code Wiki: Repository explanations should be refreshed as code changes. Read what CodeVetter learned and where our own implementation begins and ends.

Showing 50 of 1834 pages; the catalog lists all public routes.

## Machine-readable

- [Full content](https://codevetter.com/llms-full.txt): Bounded public page content
- [Markdown catalog](https://codevetter.com/api/md/_catalog): All registered public routes
- [Agent catalog](https://codevetter.com/api/ai): Existing discovery contract
- [AI usage policy](https://codevetter.com/ai.txt): Permissions and attribution
- [Sitemap](https://codevetter.com/sitemap.xml): Canonical HTML pages
- [OpenAPI](https://codevetter.com/openapi.json): Public API contract