AI code review and test tools, open source

playwright leads with a score of 94. Updated from public GitHub data.

Full category: Code review and testing.

Which one?

1st pickplaywright
Cross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit
Score 94 · 100.5k stars · Apache-2.0
Switch tonx
Monorepo build system with task caching, affected-only runs and CI integration
as a close alternative (scores 94 and 93) · Score 93 · 29.5k stars · MIT
Switch toopen-code-review
Go CLI that reviews Git diffs with an LLM agent and line-level comments
as a close alternative (scores 94 and 92) · Score 92 · 53.9k stars · Apache-2.0
AI code review and test tools, open source
RankProjectAdoptionFreshnessMaintenanceAgent-readyScore
1playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit100.5k starsApache-2.0last commit Nov 202699100984594 out of 100
2nxMonorepo build system with task caching, affected-only runs and CI integration29.5k stars+111 (+0.4%) in 30 daysMITlast commit Nov 202691100928593 out of 100
3open-code-reviewGo CLI that reviews Git diffs with an LLM agent and line-level comments53.9k starsApache-2.0last commit Nov 202695100887092 out of 100

Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.

Reviews

194 out of 100

playwright

Cross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit

100.5k starsApache-2.0last commit Nov 2026

Playwright drives Chromium, Firefox and WebKit through one API, used for end-to-end tests with the Playwright Test runner, for standalone scripts such as screenshots, PDFs and scraping, and as a browser tool for AI agents. The agent paths are a CLI for coding agents and an MCP server that exposes pages as accessibility snapshots. Bindings exist for TypeScript/JavaScript, Python, .NET and Java.

Strengths

  • One API covers Chromium, Firefox and WebKit on Linux, macOS and Windows, headless or headed
  • Test runner has auto-waiting, retrying assertions, per-test browser contexts and parallel execution
  • Trace Viewer records DOM snapshots, network requests and console logs; VS Code extension adds codegen
  • Agent tooling: MCP server uses accessibility snapshots, so no vision model is needed

Weaknesses

  • Browser binaries must be downloaded separately with `npx playwright install`
  • MCP server and CLI live in separate repos, not in this one
  • Agent features are secondary; the core is a testing and automation library
  • no GPU
  • Needs Node.js, Browser binaries via npx playwright install
293 out of 100

nx

Monorepo build system with task caching, affected-only runs and CI integration

29.5k stars+111 (+0.4%) in 30 daysMITlast commit Nov 2026

Nx is a monorepo tool for TypeScript and polyglot codebases, with a core written in Rust and extensibility in TypeScript. It caches task outputs, runs only affected projects, and can be added to an existing npm, pnpm or yarn workspace with `npx nx init`. Its CI layer adds remote caching, task distribution and an AI self-healing step that proposes fixes for failed pipelines.

Strengths

  • Adopts existing package.json scripts via `npx nx init` without restructuring the workspace
  • Plugins cover Vite, Webpack, Jest, Vitest, ESLint, Gradle, Maven, .NET and Go
  • Runs only affected tasks and caches outputs of unchanged ones
  • CI integration works with GitHub Actions, GitLab and Azure

Weaknesses

  • Remote caching, task distribution and self-healing CI go through the Nx Cloud service
  • Not an AI app starter; AI features are limited to CLI agent context and CI fixes
  • Plugins and CI setup add concepts beyond plain package scripts
  • no GPU
  • Needs Node.js, Nx Cloud (optional, for remote cache and self-healing CI)
392 out of 100

open-code-review

Go CLI that reviews Git diffs with an LLM agent and line-level comments

53.9k starsApache-2.0last commit Nov 2026

Open Code Review (`ocr`) reads a Git diff, bundles related files into sub-agent review units, and sends them to a configurable LLM that can read files and search the repo. It outputs structured comments with line positions, and `ocr scan` reviews whole files without a diff. It runs locally or in CI (GitHub Actions, GitLab CI, GitFlic CI, Gerrit), with plugins for Claude Code, Codex, Cursor, Kimi Code and OpenCode.

Strengths

  • Deterministic file selection, bundling and rule matching; one sub-agent per bundle for large changesets
  • Delegation mode lets the host coding agent use its own LLM, so no OCR API key
  • Separate comment-positioning and reflection modules to improve line accuracy
  • Resumable review and scan sessions, with a browser session viewer

Weaknesses

  • Requires Git 2.41 or newer
  • Recall is lower than a general-purpose agent, per the README's own benchmark
  • Benchmark figures are the authors' own AACR-Bench comparison
  • Default mode needs an LLM provider and API key configured first
  • no GPU
  • Needs Git >= 2.41, LLM provider endpoint (unless delegation mode), Node.js/npm (for npm install)
  • Models: Built-in and custom LLM providers, Host agent models in delegation mode