QA Wolf bills like an agency. agent-qa has no paid tier, is source available, and remembers every release.

Yes, and the reason is structural rather than a feature count. QA Wolf is a managed QA service where the vendor's team builds and maintains your test coverage under a service contract, which means the asset you are building lives on their side of the line. agent-qa is a source-available QA agent with no paid tier, governed by FSL-1.1-ALv2: tests are plain-English YAML in your repository, runs execute on your laptop, in your CI, or from your coding agent, and every run writes back into memory committed beside the tests. The suite gets better at your app whether or not you renew anything.

QA Wolf is priced on quote-based annual service contracts, so the bill tracks how much you test. agent-qa has no paid tier, no seats and no platform fee; FSL-1.1-ALv2 governs permitted use. You pay for the model tokens and infrastructure you already control, on the provider you choose, and the validated action cache takes roughly 60% of the tokens off a matched rerun. Adding coverage does not add a line item.

You are re-describing intent, not porting code, which is why this is far smaller than a normal test migration. You already know your critical flows, they're what QA Wolf's team automated for you. Re-describe them as agent-qa YAML tests and the coverage comes in-house along with everything future runs learn. Run npx agent-qa init, write each critical flow as a plain-English YAML test, and let the runtime work out the selectors and the recovery. Most teams move a smoke suite in an afternoon, and there is nothing to un-pick later because the output is files in your own repository.

Yes, and from the same file. agent-qa runs end-to-end tests on web, Android and iOS with one natural-language format, one memory store and one evidence model, so a flow written once survives being pointed at another surface. QA Wolf has expanded toward mobile through its service; agent-qa gives you web plus Android and iOS from one source-available harness, without a service engagement.

Coverage is a function of writing tests, and agent-qa makes tests radically cheap to write: plain-English YAML that engineers or coding agents produce in minutes, with memory and caching keeping runs stable as the product changes. The difference is you own the coverage instead of renting the team that maintains it.