vibe-testing
Code-aware browser testing for AI coding agents
Visit aishwaryshrivastav.github.io ↗What is vibe-testing?
vibe-testing is a testing tool that helps AI coding agents verify their work by reading your codebase, running Playwright browser checks, and tracking what changed between runs. It extracts real routes and form fields from your code, then executes tests in a live browser environment. The tool generates detailed HTML reports with screenshots, API observations, console errors, and step-by-step reproduction guides for any failures.
Designed for developers using AI editors like Claude Code and Cursor, vibe-testing works as an MCP server with 14 testing tools or as a standalone CLI. It maintains a regression ledger across runs, distinguishing between fixes, regressions, known failures, and new routes—giving your coding agent continuity and context for the next iteration.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered vibe-testing automatically. Evidence: GitHub AishwaryShrivastav/vibe-testing; repo has .cursor, .cursorrules, AGENTS.md. View source.
Similar vibe-coded apps
Open-source control plane for orchestrating multiple AI coding agents
Open-source AI job search agent that runs locally in your CLI
IDE to orchestrate multiple coding agents in one workspace
AI-native engineering philosophy and plugin for coding agents
Open-source runtime layer that turns LLMs into working agents
AI framework that injects project specs into coding agents across 20+ platforms