Engineering stories, shipped.

How to Set Up Replay MCP with Codex in Under 10 Minutes

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.

How to Set Up Replay MCP with Claude Code in 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.

Episode 1 of The Greenfield Games: An Autonomous App Builder Beat Two Human Teams

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.

Loop QA

Automatic web app QA

Replay Time Travelogue: Improving Nadia’s “Debugging with AI” Results Using Replay MCP

Replay Time Travelogue: How Replay MCP Helped Find a React Bug Faster than Dan Abramov Did

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

Web Debug Bench

A new benchmark for testing agent debugging

Introducing Replay Precog: Time-Travel Debugging for Code You Haven't Written Yet

Inspired by the 2002 documentary Minority Report

Open Auto Builder

Open source tools for building apps autonomously

Communal SaaS apps

Our library of open source SaaS apps

Replace expensive SaaS tools with your own 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.

Introducing Replay Builder: Own Your Tools, Build Without Limits

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.

What we learned from organizing Vibe coding contest

Vibe-coding apps in 60 minutes

Building Apps that Work

Launching Nut as a paid service

Nut Arboretum

Building random apps

Nut Agent

Nut’s new capabilities

Async full stack Nut

Upcoming improvements to Nut

Launching Nut.new

Helping you fix bugs without coding

The Nut API

Our new API for chatting with recordings

Nut.new

Soft launching our Bolt integration

Building a Better Bolt

On accessible software development

Autofixing clients after API changes

We use Replay+OpenHands to automatically fix a client to handle a new data format

Learning to debug

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.

Changelog 71: AI development with Replay and OpenHands

We show our prototype integration with OpenHands for reliable AI development