
Replay QA tests the app you built with AI
Replay QA runs real browser tests on AI-built apps, records every session, finds bugs, and gives builders proof their app works before launch.
Replay.io Blog
Product updates, case studies, and debugging insights from the Replay team.

Replay QA runs real browser tests on AI-built apps, records every session, finds bugs, and gives builders proof their app works before launch.

Connect Replay's MCP server to Codex CLI so your terminal agent can investigate browser recordings autonomously - DOM state, React trees, network timing - without you reproducing the bug. Setup takes under 10 minutes.

Learn how to connect Replay's MCP server to Claude Code so your agent can debug with full browser recordings, React component trees, and network timing. Setup takes under 10 minutes.

Two human teams competed, The Data Dawgs and America's Next Top Models, six experienced developers total. Running alongside them, without their knowledge, was a third team: C.H.A.D.S. (Continuous Humanless Agentic Development System), an autonomous AI agent loop powered by Replay’s time-travel debugger.

Automatic web app QA


An example of how Replay MCP enables agents to find and fix deep bugs

A new benchmark for testing agent debugging

Inspired by the 2002 documentary Minority Report

Open source tools for building apps autonomously

Our library of open source SaaS apps

Using Replay Builder, we’re creating and maintaining a library of free, open source SaaS apps. These cover a wide variety of business and personal needs, and the set of apps and their features is growing continuously.

Today we're launching Replay Builder: unlimited app building with no token limits, flat pricing, and production-ready apps you can start with. Build as much as you want, for as long as you want, for one price.

Vibe-coding apps in 60 minutes

Launching Nut as a paid service

Building random apps

Nut’s new capabilities

Upcoming improvements to Nut

Helping you fix bugs without coding

Our new API for chatting with recordings
Soft launching our Bolt integration
On accessible software development
We use Replay+OpenHands to automatically fix a client to handle a new data format

This post is the story of how we’re giving AI devs the tools they need to be successful and the incredible results we’re beginning to see as a result. The story starts with fixing failing browser tests, but progresses towards a general purpose AI dev.