# TestMu AI (formerly LambdaTest): The AI Testing Platform for your Apps and AI Agents

> TestMu AI (formerly LambdaTest) is an AI testing platform that tests web and mobile apps, chat and voice agents, and agent-to-agent workflows, then hands you the evidence.

- Start free: https://www.testmuai.com/register/
- Book a demo: https://www.testmuai.com/contact-us/
- A Leader in the 2026 Gartner® Magic Quadrant™ for Agentic Software Quality Assurance Platforms (see note at end)

## Proof

18,000+ enterprises and 3M+ users in 132 countries have run 1.5B+ tests on TestMu AI. (Source: https://www.testmuai.com/about/)

- 78%: Boomi runs its tests 78% faster on HyperExecute and tripled its automated test coverage. "We have tripled our tests and are now executing tests in less than 2 hours." (Hrishi Potdar, Quality Engineering Architect, Boomi) Source: https://www.testmuai.com/customers/boomi/
- 2.7M: Best Egg ran 2.7 million automated web and mobile tests on HyperExecute, with test execution 4x faster. "The thing that LambdaTest (now TestMu AI) has helped us do is figure out a more productive way of seeing the health of our system and addressing failures in a lower environment." (Tenny Agustin, Engineering Operations Lead, Best Egg) Source: https://www.testmuai.com/customers/best-egg/
- 70%: Transavia runs its tests 70% faster on TestMu AI after its old testing platform was discontinued. "With efficient cross-browser testing and 70% faster test execution, LambdaTest (now TestMu AI) helped us achieve faster time-to-market and enhanced CX. Their support and cost-effectiveness exceeded our expectations." (Daniel de Bruijn, Quality Assurance Automation Engineer, Transavia) Source: https://www.testmuai.com/customers/transavia/

Customers include: Microsoft, OpenAI, NVIDIA, Whatfix, GitHub, Best Egg, Workday, Akamai, Louis Vuitton, NBCUniversal, City Furniture, Cox, Raiffeisen Bank, Estée Lauder, Tripadvisor, boohoo.

## Where are you starting?

### Startup: give your Coding Agent a Tester

1. **Install Kane CLI**: Sign in with OAuth.
1. **Describe a flow**: Kane runs it.
1. **Gate on the exit code**: 1 files a bug.

[Start for free](https://www.testmuai.com/register/). Needs Node 18+.

### Growing Team: a Verdict on every Pull Request

1. **Keep your suites**: Run them on HyperExecute.
1. **Add the GitHub Action**: Kane CLI posts the verdict.
1. **Test your agents**: With Agent Testing and Rook.

[Compare plans](https://www.testmuai.com/pricing/). Paid plans from $17/mo.

### Enterprise: one Release Gate for every Team

1. **Cover every lane**: Apps and agents.
1. **Choose where data lives**: US, EU or on-prem.
1. **Connect identity**: SAML SSO and SCIM.

[Book a demo](https://www.testmuai.com/contact-us/). Your inputs and outputs are never used to train any LLM models.

## Everything you can test with TestMu AI

### Apps People Use

- [AI test automation](https://www.testmuai.com/kane-ai/): KaneAI turns plain English into end-to-end tests and replays them deterministically.
- [AI testing agent for the terminal](https://www.testmuai.com/kane-cli/): Kane CLI: browser tests your coding agent writes and runs in CI.
- [Cross browser testing](https://www.testmuai.com/cross-browser-testing/): Manual and automated tests on 3,000+ browsers.
- [Real device testing](https://www.testmuai.com/real-device-cloud/): Real Device Cloud: 50,000+ real mobile devices.
- [Visual regression testing](https://www.testmuai.com/visual-testing-tool/): SmartUI compares screenshots against an approved baseline.
- [Accessibility testing](https://www.testmuai.com/accessibility-testing/): Finds accessibility issues in sites and apps.

### AI Agents

- [AI agent testing](https://www.testmuai.com/agent-testing/): Agent Testing covers chatbot testing, voice agent testing and IVR testing with simulated customers.
- [AI assurance for agent workflows](https://www.testmuai.com/agent-assurance/): Agent Assurance (Rook) tests agents that call tools and other agents.
- [Browsers for AI agents](https://www.testmuai.com/browser-cloud/): Browser Cloud: cloud browsers your agents drive through Playwright.

### Run and manage

- [Test orchestration](https://www.testmuai.com/hyperexecute/): HyperExecute runs Selenium, Playwright, Cypress and Appium up to 70% faster than a traditional grid.
- [Test case management](https://www.testmuai.com/test-management/): Test Manager: manual and automated test cases in one place.
- [Test analytics](https://www.testmuai.com/test-analytics/): Test Insights puts results from every TestMu AI product in one view.
- [Test intelligence](https://www.testmuai.com/test-intelligence/): Flaky test detection, AI root cause analysis and failure clustering for CI/CD.

## How TestMu AI works

### AI builds it

Coding agents open pull requests faster than you can review them. Often the only check is the agent that wrote the change.

### TestMu AI verifies it

Separate agents test the release on real devices and browsers, and talk to your AI agents like customers do.

### You keep the Evidence

Every run keeps steps, screenshots, video, logs and a verdict, ready for your release gate and your auditor.

## Run AI Tests from your Terminal and CI

One command runs your tagged tests in parallel and returns an exit code for CI or your coding agent.

Kane CLI exit codes: 0 = pass, 1 = fail, 2 = setup or sign-in, 3 = timeout.

```sh
npm install -g @testmuai/kane-cli
kane-cli login --oauth
kane-cli testrun run --tags smoke --parallel 4 --headless --on-failure fail-fast
```

### Paste this to your Coding Agent

```text
Read https://www.testmuai.com/llms.txt. Install Kane CLI with npm install -g @testmuai/kane-cli and run kane-cli login --oauth, then ask me to approve the sign-in. Write a plain-English test for our checkout flow, run it with kane-cli testrun run --headless, and report the exit code and the .evidence path. Ask me before choosing any paid plan.
```

## TestMu AI Pricing

- **Free** ($0): Try it on a real project first. KaneAI free tier; 10,000 Kane CLI credits for 30 days; 300 HyperExecute minutes.
- **Paid plans** (From $17/mo): A verdict and evidence on every pull request. KaneAI from $17/mo; Agent Assurance from $44/mo; HyperExecute and real devices.
- **Enterprise** (Custom): One release gate for all your apps and agents. SAML SSO, SCIM, SOC 2 Type II, ISO 27001; US or EU data residency; Private cloud or on-prem.

Billed annually. Full list: https://www.testmuai.com/pricing/ or https://www.testmuai.com/pricing.md.

## FAQ

### What is TestMu AI?

TestMu AI is an AI testing platform for apps and AI agents, made by LambdaTest, Inc. KaneAI and Kane CLI test web and mobile apps. Agent Testing tests chat and voice agents, and Agent Assurance (Rook) tests agent-to-agent workflows. Tests run on HyperExecute, 50,000+ real devices and 3,000+ browsers.

### Is TestMu AI the same as LambdaTest?

Yes. LambdaTest renamed itself TestMu AI on January 12, 2026. The company is still LambdaTest, Inc., and existing products such as HyperExecute, SmartUI and the Real Device Cloud carried over under the new name. The platform now also tests AI agents, with Agent Testing and Agent Assurance.

### How do you test AI agents?

From the outside, the way customers and other agents meet them. Agent Testing sends simulated callers to chat, voice, phone and IVR agents, and 15+ evaluator agents score each conversation. Rook maps what an agent can do, writes adversarial tests against it and reports each check as pass, fail or unable to verify.

### Does TestMu AI replace evals?

No, it complements them. Evals score a model while you build it. TestMu AI tests the shipped app or agent from the outside, including the tools it calls, using agents that did not write the code. Run evals during development and TestMu AI before and after each release.

### How much does TestMu AI cost?

You can start free. KaneAI has a free tier, Kane CLI includes 10,000 credits for 30 days and HyperExecute includes 300 free minutes. Paid plans are billed annually and start at $17/mo for KaneAI and $44/mo for Agent Assurance. Enterprise pricing is custom, and Agent Testing is priced with sales.

### Is my data used to train AI models?

No. Your inputs and outputs are never used to train any LLM models. TestMu AI holds SOC 2 Type II and ISO 27001, supports GDPR, SAML SSO and SCIM, and offers US or EU data residency. Enterprise plans can also run in a private cloud or on-prem.

### Can AI coding agents use TestMu AI?

Yes. A coding agent can install Kane CLI with npm install -g @testmuai/kane-cli, or Rook with npm install -g @testmuai/rook@latest, and connect the MCP server at https://mcp.lambdatest.com/mcp. It can read /llms.txt and /pricing.md for context. A person approves sign-in and any paid plan.

## Built for the enterprise

Enterprise-grade security, privacy, and compliance, with the controls, support, and scale your teams need. [Contact Sales](https://www.testmuai.com/contact-us/) or [book a demo](https://www.testmuai.com/contact-us/).

---

## More for agents

- llms.txt: https://www.testmuai.com/llms.txt
- Pricing as Markdown: https://www.testmuai.com/pricing.md
- MCP server: https://mcp.lambdatest.com/mcp (Streamable HTTP, OAuth). Tools cover HyperExecute, automation logs, accessibility and SmartUI. Add it with `claude mcp add --transport http mcp-lambdatest https://mcp.lambdatest.com/mcp`. Works in Cursor, Claude Code, Copilot, Codex and Antigravity.
- Kane CLI: `npm install -g @testmuai/kane-cli`, agent skill `npx @testmuai/kane-cli-skill`, guide https://www.testmuai.com/kane-cli-agent/AGENTS.md
- Rook (Agent Assurance): `npm install -g @testmuai/rook@latest` or `brew install lambdatest/rook/rook`, agent skill `npx @testmuai/rook-skill`
- Agent guides: https://www.testmuai.com/kane-cli/agents.md, https://www.testmuai.com/agent-testing/agents.md, https://www.testmuai.com/kane-ai/agents.md
- Spending rule: a person approves sign-in and any paid plan.

* Gartner, Magic Quadrant for Agentic Software Quality Assurance Platforms, Ross Power, Sushant Singhal, C.A. Swan, 12 October 2026. Gartner does not endorse any company, vendor, product or service depicted in its publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner publications consist of the opinions of Gartner's business and technology insights organization and should not be construed as statements of fact. Gartner disclaims all warranties, expressed or implied, with respect to this publication, including any warranties of merchantability or fitness for a particular purpose. GARTNER and MAGIC QUADRANT are trademarks of Gartner, Inc. and/or its affiliates. Customer results are each customer's own. Demos show sample runs.
