🔍 Code Review & Testing

Plan-first workflow around the coding agent you already use (Claude Code, Codex, Cursor, Grok, Antigravity, Pi, OpenCode, Copilot): each change goes through Discuss, Research, Plan, Outline, Implement, Verify and Review. You approve the plan from diagrams and clickable mockups, the agent builds test-first, and a separate agent that didn't write the code reviews it. Runs locally on your own subscription. Launched on Product Hunt Nov 4 2026.

Est. monthly spend: Unknown

Autonomous AI QA for web apps: give it your URL and logins and it discovers user flows, writes end-to-end tests, self-heals when the UI changes and explains failures with video. Reports to Jira, Linear, Notion and Slack. Handy for vibe-coded apps with no QA. Launched on Product Hunt Nov 3 2026.

Est. monthly spend: Free · est.

Open-source game tester from Ramen (Oct 30 2026) that plays your game in real time inside Unreal Engine 5, Unity 6 or Godot 4 on Windows and macOS. Give it a plain-English prompt like exploring a level, verifying that a tree shakes when hit, or beating a boss, and it reads your project's code, plays, and writes a bug report. It learns the game the more it plays, and also runs from Claude Code or Codex through its skills and MCP server.

Est. monthly spend: Free · est.

A Git-compatible code host from former GitHub CEO Thomas Dohmke, built for code written by agents. Trails replace pull requests with review agents that score every push for quality, security and slop, and your agent sessions and prompts are stored alongside the code.

Est. monthly spend: Free–$50/mo · est.

Runtime bug and vulnerability hunter. It learns how to run your app in a production-like sandbox, hunts for bugs, security holes and performance issues that code review misses, and files only what it can reproduce, each with a failing test your coding agent can fix.

Est. monthly spend: Unknown

Makes your coding agent verify its own work: it drives the running app, reads network calls, app state and console, and returns a pass, fail or can't-tell verdict with the file and line to fix.

Est. monthly spend: Unknown

AI-powered code review and governance platform that generates tests and enforces coding standards.

Est. monthly spend: Free–$30/mo · est.

AI coding assistant with deep codebase understanding and context-aware suggestions.

Est. monthly spend: Unknown

AI code reviewer that provides contextual feedback on pull requests with actionable suggestions.

Est. monthly spend: Free–$30/mo · est.

AI-powered code review that understands your entire codebase to catch bugs and security issues.

Est. monthly spend: Free–$30/mo · est.

Free source-code security scanner for AI-built apps with 55 checks for exposed keys, open database tables, missing login and ownership checks, and unsafe input.

Est. monthly spend: Free · est.