The TestSprite CLI is now live — open source.

Every code change, verified end to end.

Your team and your coding agents write the code. Our testing agent verifies it independently against what your product should do, with evidence at every step. Build at full speed. Ship with proof.

Get started free

I. New release

Introducing TestSprite 4.0and our new testing agent.

It remembers what your app should do and checks all of it, every time.

II. One engine, every surface

Browser, terminal or CI— the same verifier.

However you build, TestSprite meets you there: the agent in your browser, for the whole team, a CLI for coding agents, a gate on every merge, and its results in the tools your team already uses. One suite, one set of results, whoever triggered the run.

Works with the agents and IDEs you already use.

  • Claude Code
  • Codex
  • Cursor
  • Antigravity
  • VS Code
  • Kimi
  • Trae
  • Browser · the agent

    Tell it what to test, in your own words.

    Open the agent in your browser and say what matters, or point it at your PRDs and tickets. It sets up the project, explores your app, writes the tests and runs them, and every run lands where the whole team can read it, with no code and no setup.

    • Brief it in plain words, or hand it your PRDs and tickets
    • Watch every run step by step, and replay any of them
    • Results, history and schedules the whole team can read
  • CLI · for coding agents

    A verifier that lives in the terminal.

    Open-source under Apache 2.0 and built for agents that run unattended overnight. One command, no human in the loop — and the same results land in the dashboard for everyone else to read.

    • Frontend and backend verification from one command
    • JSON failure bundles built for agents to read
    • Open source · github.com/TestSprite/testsprite-cli
  • CI · every merge

    Nothing merges unverified.

    Wire TestSprite into GitHub Actions and every pull request is re-checked against the full, growing suite before it lands. Results post to the PR, so the decision is on the record where the review already happens.

    • GitHub Action and CI integration
    • Every PR checked against the whole suite, not a sample
    • Results posted to the PR for the reviewer to see
  • Integrations · where your team works

    Failures land where your team already works.

    Connect Linear or Jira and a failing test becomes a bug ticket in one click. Connect Slack and every finished run posts its summary to a channel. GitHub checks every pull request. Nobody has to open a dashboard to hear about a failure.

    • Bug tickets for failing tests, in Linear or Jira
    • A summary in Slack whenever a run completes
    • Every pull request checked through GitHub

III. Why TestSprite

Not another test runner.A QA loop your agent drives.

Three things make the difference between shipping fast and shipping broken.

IV. Always on

It keeps running after you close the tab.

A verifier that runs when someone remembers to run it protects nothing. Give it a schedule and a merge gate.

  • Every merge

    A gate, not a report.

    Every pull request is re-checked against the full suite before it lands, and the result posts to the PR — where the review already is.

  • Every night

    Re-verified on a cadence you set.

    Nightly, weekly, or ahead of each release. Silent breaks surface on their own instead of during a demo.

  • Every run, kept

    Every run is kept, not overwritten.

    Verdict, video and trigger, all retained — so you can see when a test started failing, not just that it is.

V. Customer stories

Teams who ship every day,and know what they shipped.

  • “Good job! Pretty cool MCP from TestSprite team! AI coding + AI testing helps you build better software easily!”

    Trae TeamByteDance - Trae AI
  • “I’m generating code faster than ever, but that also means bugs can compound just as fast. TestSprite catches what Cursor misses. The fact that it runs automatically on every pull request means my team can move quickly without second-guessing what just merged.”

    Hang H.CEO - InstaCloud
  • “TestSprite's user-friendly interface made it easy to set everything up. The simplicity of the onboarding process really sets TestSprite apart from other tools we've used in the past.”

    Jeffery Z.Managing Partner - Princeton Pharmatech
  • “TestSprite's automation has been invaluable in detecting hard-to-find issues. API testing is crucial to our product. Its comprehensive coverage gives us confidence to release updates without concerns of breaking the backend.”

    Malcolm Y.Co-founder - Genrex
  • “TestSprite is one of the most exciting AI startups in the world. It is an autonomous software testing platform where AI agents generate and execute tests to validate that software actually works — across codebases, environments, and the live web.”

    Homer W.Head of Product - TinyFish
  • “TestSprite offers rich test case generation, clear structure, and easy-to-read code. It also supports simple online debugging with the ability to quickly expand by generating new test cases.”

    Bo L.QA Engineer - Luckin Coffee

VIII. Good to know

Frequently askedquestions

It’s a testing agent that checks your app against what it should do. Tell it in your own words, or point it at your PRDs and tickets; it writes the end-to-end tests (frontend and backend), runs them against your running app, and keeps them current as the interface changes. Every failure comes back as a real bug, a test problem or an environment issue, with a replay, the failing step, and expected versus actual. It runs from the web app, your terminal (the CLI is open source under Apache 2.0), your IDE through MCP, or on every pull request.

PL. III — Claude Monet, Vétheuil

Ship at AI speed.Merge knowing nothing broke.