|
Codesurf | GitHub Pull Request Check & AI Code Review Tool
Codesurf is a GitHub-native AI pull request reviewer that catches bugs, security issues, and risky vibe-coded changes before merge. Install the GitHub App, r...
|
81 % |
|
VibeCheck — AI-Powered Code Review
Get your code vibe-checked by AI. Plain English explanations, trust scores, and fix suggestions for non-developers.
|
81 % |
|
Iris Code - Keep AI-assisted code up to your standards
Give coding agents your project rules, check every change independently, and enforce the same standard in your editor, hooks, and CI.
|
81 % |
|
ReviewPilot — AI code reviews your team can actually trust
ReviewPilot combines deterministic analysis with a multi-stage AI review pipeline to deliver focused, high-quality pull request feedback directly inside GitHub.
|
81 % |
|
Tight Code · AI security and code review at push time
A git pre-push hook that runs in Claude Code and reviews every push on your own machine, under the Claude Code login you already have. Option to add OpenAI's...
|
81 % |
|
Polka Codes - AI Code Assistant
AI-powered code assistant for developers. Get instant code suggestions, completions, and workflow automation that understands your context and codebase.
|
80 % |
|
noSwag: Agentic Tests for AI-Built Apps
Agentic test generation for vibe-coded apps and AI-generated code dumps. noSwag turns messy code into reviewable pytest and Vitest files your team can own.
|
80 % |
|
Judge — Score every iteration. Catch the regression before it ships.
Score any output your team iterates on — code, content, AI features, designs. Typed metrics, delta vs. last run, cited evidence. GitHub App, CLI, TypeScript...
|
80 % |
|
CodeAudit — Check if your AI-built app is actually safe and correct
Describe what your app should do, upload your code or link, and CodeAudit checks both its security and whether the code really does what you intended — expla...
|
80 % |
|
CodeGate — Agentic code review for GitHub
Most AI reviewers read your diff. CodeGate investigates the repository around it — and reviews every pull request against your project's own rules, not gener...
|
80 % |
|
CodeRifts — Know what may proceed. Prove why it did.
A fail-closed authorization-execution gate: one grant binds authorize, consume, target-state transition, and offline readback. Without this receipt the check...
|
79 % |
|
prodlint — Production readiness for vibe-coded apps
Know your vibe-coded app is production-ready before you ship. 52 checks across security, reliability, performance, and AI quality.
|
79 % |
|
arivcode — Stop shipping code you don't understand
An open-source CLI tool that quizzes developers on their code changes before committing. Built for teams using AI code generators who want accountability for...
|
79 % |
|
screencli — AI code review & browser QA for pull requests
AI code review that runs your app: screencli opens your PR preview in a real browser, clicks through the UI, and shows what broke before you merge.
|
79 % |
|
Maina — your AI keeps sending the wrong context. That's why it's slopping out broken code.
Maina is a verification-first developer OS. It rebuilds the context your AI should have been using, runs a 19-tool pipeline on every diff, and proves the cha...
|
79 % |
|
Gitsentry.dev - The Security Scanner for the AI era
AI-powered security scanner that catches vulnerabilities in AI-generated code on every PR and push. Findings posted as GitHub review comments.
|
79 % |
|
codexgrill — Adversarial plan review & security audits for Claude Code
A Claude Code plugin that grills your implementation plans with Codex (read-only) and runs full security audits — Claude validates every finding against the...
|
79 % |
|
CodeMate
AI code reviews on every pull request.
|
79 % |
|
Undes AI (Ündes) — Evidence-Checked AI Code
Undes helps developers know what is safe to merge by checking AI-generated code, patches, refactors, and architecture decisions against evidence, assumptions...
|
79 % |
|
Otta — Delivery control for coding agents.
Otta gives Claude Code and Codex a disciplined path from issue to verified release, with specialist review stages and Pulse-enforced GitHub evidence.
|
79 % |
Detected social media networks