convez.ai
Agente
sarthak-fleet

CodeVetter

sarthak-fleet/CodeVetter

Ver no GitHub
InicialPluginScore · de 0 a 100

Desktop-first AI code review for agent-generated diffs. Local Tauri app — reviews run on your machine via Claude/Codex/Gemini CLIs.

Instalação

$npx convez-ai sarthak-fleet/CodeVetter

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
25%
Último commit
há 1 dia
Versão
v1.16.7
Issues abertas
5
Contribuidores
4

README

A tradução para o português deste README ainda está na fila.

CodeVetter

AI software quality workbench for agent-generated code — desktop-first, local-first, and focused on finding bugs that normal AI review misses.

Product Direction

CodeVetter should end as a personal verification layer for AI-built software. The durable scope is:

  • code review
  • bug finding
  • agent-written code verification
  • debugging and replay
  • synthetic user QA for software quality
  • AI step-through debugging
  • codebase history explanation

The near-term wedge is not beating Claude, Codex, or hosted PR bots at generic review. It is a self-first workflow that makes agent output trustworthy: inspect the diff, understand the repo and prior intent, exercise the changed behavior, preserve evidence, fix one finding at a time, and re-check that the issue is gone.

Current Coverage And Gaps

CapabilityCurrent stateMain gap
Code reviewReview tab runs local diffs through CLI agents and persists findings.Needs multi-pass specialist review, better AGENTS.md/project-context ingestion, and benchmarked catch-rate evidence.
Bug findingFindings, severity, code viewer, and re-review loop exist.Needs runtime evidence from tests/browser sessions/logs, not only static diff judgment.
Agent-written code verificationProduct is aimed at agent output and can fix/re-review selected findings.Needs agent provenance: which agent changed what, prompt/task context, and whether the fix actually resolved the original user goal.
Debugging/replayHistory indexes Claude/Codex sessions and can replay conversations.Replay is not connected to files, diffs, failures, screenshots, tests, or review findings.
Synthetic user QANot implemented as a first-class workflow.Needs browser/app automation that performs user tasks, captures screenshots/traces, and converts failures into review findings.
AI step-through debuggerNot implemented.Needs an execution timeline across agent actions, file edits, commands, test failures, and UI observations.
Codebase history explainerRepo Unpacked generates repo briefs; History indexes agent sessions.Needs commit/decision mining tied to touched files so reviews can catch intent regressions.

The product should prefer narrow, evidence-backed loops over broad "code intelligence" surfaces. A feature is on-strategy when it helps answer: "What changed, why did the agent change it, what could break, can we reproduce it, and did the fix actually work?"

Deployment & External Services

ConcernService
Desktop appGitHub Releases — Tauri 2 macOS build, with @tauri-apps/plugin-updater auto-updater (latest.json manifest)
Landing pageCloudflare Pages (codevetter, codevetter.com) — static Next.js export
DatabaseLocal SQLite via @tauri-apps/plugin-sql (desktop only, no server)
AuthNone — LLM provider API keys stored in user settings
AIUser-supplied keys (Anthropic / OpenAI / OpenRouter)
CI/CDGitHub Actions — release.yml builds Tauri binaries on GitHub release; deploy-landing.yml deploys the landing page to Cloudflare Pages on push to main

Installation

Ask Your Agent To Install

Give your coding agent this prompt:

Install CodeVetter from the latest GitHub release:
https://github.com/sarthak-fleet/CodeVetter/releases/latest

Detect this machine's OS and CPU architecture, download the matching CodeVetter app archive, verify the release asset hash when available, extract it, install CodeVetter.app into /Applications on macOS, remove the quarantine attribute if needed, and launch the app once to verify it starts.

Prefer the app archive over the DMG until the macOS bundle is Developer ID signed and notarized.

Development Install

# Clone and install dependencies (uses npm workspaces)
git clone https://github.com/sarthak-fleet/CodeVetter.git
cd CodeVetter
npm install

Requires Rust + Tauri prerequisites for the desktop app.

Quick Start

  1. Install dependencies (see above)
  2. Launch the desktop app in development mode:
    cd apps/desktop && npm run tauri:dev
    
  3. Open the Review tab, pick a local repository, and run your first review through an installed CLI agent.

Usage Examples

Run the desktop app (dev mode)

cd apps/desktop
npm run tauri:dev

Run Playwright end-to-end tests for the desktop app

cd apps/desktop
npm test

Build the landing page

cd apps/landing-page
npm run build

Monorepo Structure

apps/
  desktop/          Tauri 2 + React 19 + Vite desktop app — the core product
  landing-page/     Next.js marketing site (static export, deployed to Cloudflare Pages — codevetter.com)

Tech Stack

LayerTechnologies
Desktop frontendReact 19, Vite, Tailwind CSS, shadcn/ui
Desktop backendRust (Tauri 2), SQLite
Review engineTypeScript — runs in the webview, no server required
Landing pageNext.js 15 (static export → Cloudflare Pages)
TestingPlaywright (e2e)
Package managernpm workspaces

License

ISC (root package); MIT (landing-page template — Copyright 2022 Themesberg)

Active AI Task Log

This section is maintained by the SaaS Maker Active-AI product/design loop so future agents do not reopen duplicate UI tasks.

  • Business lane: Core/status context
  • Rule: do not create another broad "improve the UI" task unless the acceptance criteria differ materially from the tasks listed here.
  • Source of truth for task status: SaaS Maker task board. README entries are durable context only.
Task IDTitleStatus
d6d19901CodeVetter: add verification summary handoff proofdone — compact verification summary panel added to QuickReview sidebar with fixed/reproduced/unchecked counts and copy-proof button
a59acaa7CodeVetter: add unchecked finding risk summarydone — QuickReview sidebar now lists unchecked findings grouped by severity with per-bucket risk copy explaining why each unchecked item still matters (above the verification handoff proof)
79eff0b9CodeVetter: add revalidation checklist after fixesdone — when a finding's re-check status is "fixed", QuickReview renders a checklist derived from the finding's evidence fields (file/line, artifact, level, notes) so the user can tick off concrete revalidation steps; checklist state persists per finding alongside other evidence
2b9ac8d9CodeVetter: add copyable reviewer handoff templatedone — QuickReview's "Copy proof" button now emits a full markdown reviewer handoff (heading, score/agent/finding tallies, per-finding evidence with status icons, and a ### Next actions checkbox list derived from unchecked findings, reproduced findings, and unticked revalidation items for fixed findings) so reviewers can paste proof directly into PRs/Slack
Ver o original no GitHub

Bom para

Relacionados