A browser automation alternative free to start
Most AI browser tools bill every run against a hosted browser and hand back a task summary. Kane CLI runs on your local Chrome for free, takes a plain-English objective, self-heals on UI changes, and returns a verified pass or fail. Free to install.
or read the documentation
Why teams switch browser automation tools to Kane CLI
Many AI browser automation tools price every run against a hosted browser and return an open-ended summary rather than a verdict. That gets expensive in the inner loop and in CI, and it leaves you unsure whether the flow actually worked.
Kane CLI runs on your local Chrome for free and returns a verified pass or fail. You give it intent, it drives a real browser, adapts when the UI shifts, asserts each step, and reports evidence with standard CI exit codes.
Pricing is usage-based, not per seat, and there is no lock-in: export any validated flow to native Playwright with one command, and scale to cross-browser cloud runs only when you need them.
Kane CLI vs typical AI browser tools
Free to start, verified by default, and no lock-in.
| Capability | Kane CLI (TestMu AI) | Typical AI browser tools |
|---|---|---|
| Cost to start | Free local Chrome runs, free to install | Often billed per run on a hosted browser |
| Authoring model | Plain-English objectives, no selectors | Prompts, scripts, or low-level tool calls |
| Verified pass or fail | Built-in assertions, returns pass or fail | Often a task summary, not a test result |
| Resilience when the UI changes | Autoheals and retries up to 50 steps | Varies |
| Agent-native output | --agent emits structured NDJSON | Varies |
| CI exit codes | 0 pass, 1 fail, 2 error, 3 timeout | Varies |
| Evidence and reporting | Video, step trace, shareable links, dashboard | Varies |
| Pricing model | Usage-based, not per seat | Often per-seat or per-run |
| Lock-in | Exports validated flows to Playwright | Often proprietary |
| Scale when needed | One flag for cross-browser and OS on the grid | Varies |
What you get with Kane CLI
Free local runs, a test contract, and usage-based pricing.
Free to start, free to stay local
Install at no cost and run on your own Chrome for free. There is no per-run meter on the inner loop, so verifying a flow never adds to a bill.
No selectors to maintain
Describe the journey in plain English once and Kane CLI plans the steps and drives a real Chrome. No scripts to write means no scripting cost as the UI evolves.
A verdict, not a billed summary
Built-in assertions check each step and flag the exact point of failure, so every free local run returns a real pass or fail instead of an open-ended report you paid for.
Agent-native at no extra cost
Run with --agent and the output becomes structured NDJSON an AI coding agent reads line by line, with screenshots on failure, so agents drive verified runs without a hosted-browser fee.
No lock-in, code you own
Export any validated flow to native Playwright and keep it. Pricing is usage-based, never per-seat, so you are never locked into a license or a proprietary format.
Pay only when you scale
Stay free locally, then send the same flow across browsers and operating systems on the TestMu AI grid with one flag, paying by usage for just the cloud runs you trigger.
Build up confidence locally
Start in your terminal
Validate on the cloud
Release with confidence
Built for agents and humans, on one engine
Kane CLI and KaneAI share the same automation engine and dashboard.
Start free, no card required
Spin up real browser automation on your local Chrome without paying anything. The free tier runs end to end, so you can prove the tool out before a single dollar is spent.
Usage-based, never per-seat
There is no license to renew and no seat to count. Add teammates and agents freely, and pay only for the cloud runs you actually trigger on the TestMu AI grid.
Walk away with your own code
No lock-in means no hostage situation. Export any validated flow to native Playwright with one command and own real automation code outright, whenever you decide to.
Switch to Kane CLI in three steps
Install free
Run npm install -g @testmuai/kane-cli and sign in with your TestMu AI account. No credit card, and your local Chrome powers every run at no cost.
Describe the flow
Write the journey in plain English, with no selectors or scripts to maintain. Run it from the terminal or hand it to your AI coding agent with the --agent flag.
Run free, scale when ready
Each local run returns a verified pass or fail with evidence and a shareable link, all for free. Reach for the paid grid only when you want cross-browser coverage.
Get Started With Kane CLI
🎉 Launch offer: Bonus credits for the first 3 months on paid plans
Choose the right plan for you
Local test authoring via CLI
Auto-heal & vision
View test cases on UI
Test Manager
Free
$0
/month
200 Credits
Resets in every
30 days
Starter
$19
/month
2000 Credits
Launch: 4,000 Credits (+100%)
Bonus for first 3 months
Pro
$99
/month
10,000 Credits
Launch: 15,000 Credits (+50%)
Bonus for first 3 months
Enterprise
Get access to solutions built on Enterprise-Grade Security, Privacy, and Compliances.
Need more credits?
Got a bigger use case in mind?
Let’s talk
Choose the right plan for you
Free
$0
/month
200 Credits
Resets in every
30 days
Starter
$19
/month
2000 Credits
Launch: 4,000 Credits (+100%)
Bonus for first 3 months
Pro
$99
/month
10,000 Credits
Launch: 15,000 Credits (+50%)
Bonus for first 3 months
Enterprise
Get access to solutions built on Enterprise-Grade Security, Privacy, and Compliances.
Need more credits?
Got a bigger use case in mind?
Let’s talk
Get the technical rundown
Documentation
Everything you need to install, configure, and run Kane CLI in under 2 minutes.
Frequently asked questions
Kane CLI by TestMu AI is a free-to-start alternative to paid AI browser automation tools. Where most tools meter every run against a hosted browser, Kane CLI runs on your own local Chrome at no cost, takes a plain-English objective, self-heals when the UI changes, and hands back a verified pass or fail. You only reach for the paid cloud grid when you actually need cross-browser and OS coverage.
Yes. Installing Kane CLI is free and every local Chrome run is free, so the inner loop and CI smoke checks cost you nothing. There is no per-seat license to buy. You pay only for the cloud runs you choose to spin up on the TestMu AI grid, billed by usage, which keeps day-to-day automation far cheaper than tools that charge for each hosted run.
It removes the cost barrier and the lock-in. You write what you want in natural language instead of selectors, you get a verified pass or fail instead of a billed task summary, and it stays agent-native by emitting structured NDJSON under the --agent flag. Start free locally, and when you want real code you own, export to Playwright.
Yes, and that is the no-lock-in guarantee. Any validated flow exports to native Python Playwright with one command, so even though you author in plain English on a free local run, you can walk away with real automation code you own outright. Nothing is trapped in a proprietary format.
Yes, and free local runs make it cheap to gate every build. Authenticate with your TestMu AI credentials, pass --headless and --timeout, and read the exit code in your pipeline: 0 on pass, 1 on fail, 2 on setup or auth errors, and 3 on timeout.
Yes, free to install and free to run on your local Chrome, with no credit card to start. You can run end to end on the free tier. Only cloud runs on the TestMu AI grid draw against your plan, and that is usage-based, so you never pay for capacity you do not use.
Teach your agent the right skills
Point your AI coding agent at the Kane CLI guide and it will install, authenticate, and run verified browser flows on its own.
Point your agent to: testmuai.com/kane-cli/agents.md