Kane CLI vs Picoclaw that verifies the run
Looking for local browser automation that does more than run actions? Kane CLI takes a plain-English objective, drives a real Chrome browser on your machine, self-heals on UI changes, and returns a verified pass or fail. Free to install.
or read the documentation
Why teams choose Kane CLI for local browser automation
Local automation tools are good at performing actions. The gap is verification: knowing the flow actually worked, with evidence you can replay and share.
Kane CLI closes that gap. You give it intent, it drives a real Chrome browser on your machine, adapts when the UI shifts, asserts each step, and returns a deterministic pass or fail with video evidence.
Start local and free, then scale the same flow to cross-browser cloud runs with one flag, export to native Playwright when you want the code, and let an AI coding agent drive it through the --agent flag.
Kane CLI vs Picoclaw
Local browser automation, with a verified test contract on every run.
| Capability | Kane CLI (TestMu AI) | Picoclaw |
|---|---|---|
| Authoring model | Plain-English objectives, no per-site scripts | Script-based local automation |
| Local-first | Runs on local Chrome by default | Local |
| Verified pass or fail | Built-in assertions, returns pass or fail | No built-in verification |
| Resilience when the UI changes | Autoheals and retries up to 50 steps | |
| Agent-native output | --agent emits structured NDJSON | |
| Scale to the cloud | One flag for cross-browser and OS on the grid | Local only |
| CI exit codes | 0 pass, 1 fail, 2 error, 3 timeout | |
| Evidence and reporting | Video, step trace, shareable links, dashboard | Up to you to build |
| Test Manager sync | Every run syncs automatically | |
| Native Playwright export | One command to export Playwright code |
What you get with Kane CLI
Local-first runs, verification, and evidence built in.
Local-first, free to start
Kane CLI runs on the same local Chrome a tool like Picoclaw uses, with no infra to set up. Describe a flow, get a real result in minutes, then scale that exact flow to the cloud with one flag.
It verifies, it does not just act
Running the action is half the job. Kane CLI asserts each step locally and returns a clean pass or fail, so every local run is a verified test rather than a fire-and-forget action.
Holds up when the local UI shifts
Selectors break and local scripts go stale. Kane CLI reads intent, adapts on its own when the page changes, and pushes through up to 50 steps until the full journey is verified.
Drives an agent, not just a browser
The --agent flag turns local automation into a feedback loop: structured NDJSON your AI coding agent parses directly, plus screenshots to read on failure.
Local runs that gate CI
Take the same local flow into a pipeline with standard exit codes and no custom scripting: 0 pass, 1 fail, 2 error, 3 timeout.
Own the Playwright code
Export any locally validated flow to native Playwright, then modify and own it. Convenience now, no lock-in later.
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.
Local automation that also checks itself
Kane CLI runs flows on your own Chrome like a local tool, but every run carries built-in assertions, so you get a verified pass or fail instead of an action that may or may not have worked.
From your laptop to the cloud grid
Prove a flow locally and free, then run the same plain-English journey across browsers and operating systems on the TestMu AI grid with one flag. No rewrite, no second tool.
Proof every local run leaves behind
Each run captures a persistent video, a step trace, and a replay link, so a local pass is something you can hand to a teammate, drop in a PR, or attach to a bug report.
Switch to Kane CLI in three steps
Install and sign in
Run npm install -g @testmuai/kane-cli, then sign in with your TestMu AI account. It automates your local Chrome, the same place a tool like Picoclaw runs.
Describe the flow
Write the local journey in plain English instead of selectors or a script. Run it from the terminal yourself, or hand it to your AI coding agent with the --agent flag.
Run, verify, scale
Kane CLI runs the flow on your machine, asserts each step, and hands back a pass or fail with video and a replay link. Add one flag to repeat it across browsers on the cloud grid.
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
Picoclaw is a local browser automation tool that runs actions on your machine. Kane CLI runs locally too, but it treats each run as a test: you describe an objective in plain English, it self-heals on UI changes, and it returns a verified pass or fail with video evidence. Local runs are free, and one flag scales the same flow to the cloud grid.
Like a local tool such as Picoclaw, Kane CLI runs on your own Chrome by default. It works through natural-language intent instead of per-site selectors or scripts, so you sign in once with your TestMu AI account and run flows against any site from the terminal. There is no per-site integration to wire up.
A local automation tool performs the action; Kane CLI confirms it. It checks each step against built-in assertions, returns a clean pass or fail, captures video and a step trace, and exits with standard CI codes. It also emits structured NDJSON under the --agent flag so an AI coding agent can drive it.
Yes. Any validated flow exports to native Python Playwright with one command, so you author in natural language and keep ownership of real automation code whenever you want it.
Yes. Where a local-only tool stops at your laptop, Kane CLI is built to gate pipelines. Authenticate with your TestMu AI credentials, pass --headless and --timeout, and key your pipeline off the exit code: 0 on pass, 1 on fail, 2 on setup or auth errors, and 3 on timeout.
The CLI is free to install and use, and local Chrome runs are free, the same place a tool like Picoclaw operates. Cloud runs on the TestMu AI grid are billed against your TestMu AI plan. Start on the free tier and run end to end without a credit card.
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