BotGauge
Freemium
Startups and fast-moving engineering teams
Catcher
FreeOpen SourceSelf-HostedAgentic
Most AI testing tools run your tests on their cloud, with their LLM, on their timeline — which means the moment you have a compliance requirement or a cost spike, you're stuck. Catcher is a local-first, MIT-licensed desktop app that runs browser tests on your own machine, against your own LLM API key.
Similar tools
BotGaugeFreemiumThe core loop is: probe the agent with adversarial and real-world scenarios, trace every…
AxonQAFreemiumThe core loop: bring in a Jira ticket or let the AI explore your app, review the tests it…
Before Users DoPaidThe tool connects to MCP-compatible clients like Cursor or Claude Desktop, so the QA loop runs…
Bypass LabsPaidThe workflow is boundary-in, proof-out: you approve targets, exclusions, and stop conditions…
Get This Tool
License: MIT Any use incl. commercial
Local-run terms: MIT license permits free use, modification, and commercial deployment without restriction. Users must provide their own LLM API keys and pay the provider directly.
Screenshots 1
Pricing
- Model
- Free
Summary
You describe tests in plain English, and Catcher's LLM-powered planner executes them in a real browser — no script authoring, no Selenium boilerplate. The vision-based fallback handles dynamic UIs where element selectors break, which is where most scripted test frameworks quietly start failing your CI. Because you supply the API key directly, LLM costs land on your own account — nothing is proxied through a vendor margin. The ceiling arrives when you need a test management dashboard, CI pipeline integrations, or a shared test artifact store across a team: the repo describes none of those, and you are building that infrastructure yourself.
Bottom line: Pick Catcher when you need to automate browser tests on a locked-down or air-gapped machine and can accept a manual CI integration story; look elsewhere the moment your team needs shared test runs, results dashboards, or a maintained plugin ecosystem.
Find your fit
Before you choose Catcher
More options in Test Generation. Compare pricing, platforms, and features side by side.
AxonQA
Freemium
QA engineers and teams shipping software
Pros
- Local execution with BYOK LLM routing, so teams under data residency or compliance requirements can run AI test automation without sending application traffic to a third-party SaaS.
- LLM-provider agnostic configuration — OpenAI, Claude, Gemini, or a local Ollama model — so switching providers when API costs spike is a configuration change, not a vendor negotiation.
- Vision-based recovery for dynamic UIs, so tests against pages where selectors shift on each render don't silently fail the way Selenium or Playwright scripts do when the DOM changes.
- Plain English test authoring, so QA engineers who don't write automation scripts can produce and maintain test suites without a developer in the loop on every update.
- MIT license with full source access, so teams can audit exactly what the planner is doing with their credentials and page content — no black-box cloud execution.
Cons
- No built-in CI integration or API surface: wiring Catcher into a pull request pipeline requires wrapping a desktop Electron app externally, which is an unsupported path the docs don't describe. Teams that need automated test triggers on every commit typically abandon this and move to a headless-capable framework like Playwright with an LLM layer bolted on.
- No shared test results, artifact storage, or team dashboard: when a test fails, the output lives on the machine that ran it. Teams with more than one QA engineer coordinating on a shared test suite are managing that coordination entirely outside the tool.
- LLM planner reliability is bounded by prompt quality and model behavior: the repo ships a prompt writing guide precisely because poorly authored descriptions produce unreliable execution. Teams without the patience to tune prompts per test scenario will hit a wall before covering a non-trivial test suite.
- Early-stage repo with 19 commits and zero open issues at publication time — not because nothing breaks, but because the community surface is too small to surface failure patterns. Production adoption without a larger user base means you are discovering edge cases without a community history to search.
About
- Platforms
- Windows, macOS
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- June 1, 2026
Best For
Who it's for
- Teams wanting AI test automation without SaaS lock-in
- QA engineers who prefer natural language test descriptions
- Organizations with data residency or compliance requirements
- Users seeking LLM flexibility (OpenAI, Claude, Gemini, Ollama, etc.)
- Companies wanting to avoid cloud test execution fees
What it does well
- Natural language web test authoring without script coding
- End-to-end browser testing with visual recovery for dynamic UIs
- Regression testing for internal tools and web applications
- QA automation with LLM flexibility and cost control
- Testing proprietary applications in air-gapped environments
Integrations
Compare Catcher
Frequently Asked Questions
- Is Catcher free?
- Catcher offers a free option. Hosting, model usage, or optional services may have separate costs; check the pricing details and official terms.
- Is Catcher open source?
- Yes. Catcher is open source — the source repository is at https://github.com/catcher2026/catcher.
- Can I self-host Catcher?
- Yes. Catcher supports self-hosting on your own infrastructure.
- What platforms does Catcher support?
- Catcher is available on: Windows, macOS.
People also compared
Catcher is an open-source desktop application for AI-driven web testing. You write test descriptions in plain English — no code, no selectors — and the tool uses a connected LLM to plan and execute a multi-step sequence in a real, local browser. The LLM acts as a planner: it reads the page, decides what to click or type, and recovers from dynamic UI changes using vision-based fallback when the DOM shifts unexpectedly. The full execution happens on your machine.
The defining architectural choice is local-first, bring-your-own-key (BYOK). Unlike SaaS testing platforms that proxy your tests through their infrastructure, Catcher connects directly to whichever LLM provider you configure — OpenAI, Claude, Gemini, or a local Ollama instance. That means teams with data residency requirements or air-gapped environments can run AI-assisted test automation without routing traffic through a third-party cloud. It also means LLM spend is visible and controlled at the provider level, not hidden inside a platform subscription.
Catcher fits teams that want to eliminate script-writing overhead for internal tools or regression suites and are willing to manage their own infrastructure around it. The gap appears at team scale: the repo documents no shared test artifact storage, no built-in CI trigger mechanism, and no results dashboard. A solo QA engineer or a small team evaluating AI test authoring will find it moves fast. A team that needs to wire test runs into a pull request gate or share failing screenshots across a squad is stitching that workflow together themselves.
The project is MIT-licensed, self-hosted as a desktop Electron app, and includes a prompt writing guide to help users author test descriptions the planner handles reliably. There is no API surface exposed for external orchestration, so programmatic test scheduling requires wrapping the desktop app externally — a workaround the vendor does not document.
Contribute
- Work on Catcher? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.