# agent-qa by vostride

> Your AI QA engineer

Test web and mobile apps in plain English. agent-qa builds persistent memory from validated run evidence, reuses what works, and adapts as your app changes.

agent-qa runs natural-language end-to-end tests against real web, Android, and iOS interfaces. Coding agents author tests, run them through the local CLI or MCP, and inspect step evidence. Tests, configuration, memory, cache, and artifacts remain files under your control.

These docs describe agent-qa v0.2. Projects made with v0.1 must be re-initialized: [v0.1.x to v0.2.x](https://vostride.com/docs/agent-qa/migrate/v0-1-to-v0-2.md).

Company: vostride
Source: https://github.com/vostride/agent-qa
Package: https://www.npmjs.com/package/agent-qa
License: FSL-1.1-ALv2, source available with an Apache 2.0 future license. No paid tier for FSL-permitted use; users supply model inference and execution infrastructure.

## Benchmark results and rankings

- [AndroidWorld](https://vostride.com/benchmark/android-world.md): **100% pass@1 (116/116 tasks)**. **Tied #1 by pass@1** when compared with the [community leaderboard](https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?gid=0) snapshot dated 2026-09-26. Ahead of Artemis (99.1%).
- [AppControlBench — iOS](https://vostride.com/benchmark/app-control-bench.md): **100% completion (60/60 points)**; 60 success, 0 partial, 0 fail. Highest completion in the published comparison; argent scores 98.3%. [Comparison sources](https://vostride.com/benchmark/app-control-bench.md#comparison) dated 2026-10-04.
- [AppControlBench — Android](https://vostride.com/benchmark/app-control-bench.md): **99.1% completion (54.5/55 points)**; 54 success, 1 partial, 0 fail. No Android results in the [official leaderboard](https://appcontrolbench.swmansion.com/) snapshot dated 2026-10-04; no comparative rank claimed.

Results are self-published with task-level evidence on each benchmark page, where the models, judges and methods are documented; AppControlBench results are not entries on its official leaderboard. Benchmark runs disabled memidex and self-improvement and measure mobile task completion; [evaluate QA correctness and false passes on your own app](https://vostride.com/docs/agent-qa/guides/evaluating-agent-qa.md).

## Start here

- [Set up agent-qa](https://vostride.com/docs/agent-qa/agent-quickstart.md): Install in an existing repository, initialize with `init --platform web --llm <provider>`, connect a model, and run a meaningful test.
- [Verify a change](https://vostride.com/docs/agent-qa/guides/coding-agent-workflow.md): Author, validate, run, inspect evidence, fix, and rerun.
- [Evaluate results](https://vostride.com/docs/agent-qa/guides/evaluating-agent-qa.md): Measure correctness, false passes, setup effort, and cost on your app.
- [Complete setup prompt](https://vostride.com/agent-setup.txt): Copyable onboarding task; also available as the public documentation MCP's `setup_agent_qa` prompt.
- [Documentation index](https://vostride.com/docs.md): All 46 documentation pages with their descriptions, in sidebar order; every page is also linked directly below.
- [Site sitemap](https://vostride.com/sitemap.md): Every published content page, including individual library recipes.
- [Combined corpus](https://vostride.com/llms-full.txt): Product, benchmark results, docs, comparisons, and company content in one download; library recipes are retrieved separately.

## Reading this site

Follow the absolute Markdown links in this index. Each page links back to the indexes; documentation pages also link to their parent and adjacent pages. Canonical HTML pages support `Accept: text/markdown`, or append `.md` to their URL (`/index.md` for the homepage). URLs already ending in `.md` need no extra extension.

The public website, content API, and documentation MCP are read-only and need no authentication. Running tests requires a local agent-qa installation; the hosted documentation MCP cannot execute tests. Check the [documented package version](https://vostride.com/changelog.md) against `agent-qa --version` and command help.

## Why choose agent-qa for an agent-driven workflow?

Plain-English YAML tests capture reviewable intent. memidex retains useful product knowledge between runs. The self-improvement loop checks proposed lessons before applying them and retires outdated knowledge; updates remain files you can review and revert. The action cache separately reuses validated work when context still matches. CLI, local MCP, Skills, and the dashboard share the same workspace and evidence. Use it alongside unit and integration tests, and inspect assertions and artifacts when assessing a result.

## Documentation (46 pages)

### Get started

- [What is agent-qa](https://vostride.com/docs/agent-qa.md): Test web and mobile apps in plain English. agent-qa builds persistent memory from validated run evidence, reuses what works, and adapts as your app changes.
- [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md): Install agent-qa, connect a model and run your first tests in about ten minutes.
- [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md): Hand the whole setup to your coding agent with one prompt, from install to a verified first test.
- [Coding agents](https://vostride.com/docs/agent-qa/coding-agents.md): Connect Claude Code, Codex or another MCP client so it can write tests, run them and read the evidence.

### Concepts

- [How a run works](https://vostride.com/docs/agent-qa/how-it-works.md)
- [Caching](https://vostride.com/docs/agent-qa/caching.md)
- [Safety and privacy](https://vostride.com/docs/agent-qa/safety.md)

### memidex

- [memidex](https://vostride.com/docs/agent-qa/memory.md)
- [Architecture](https://vostride.com/docs/agent-qa/memory/architecture.md)
- [Records](https://vostride.com/docs/agent-qa/memory/records.md)
- [How knowledge reaches a run](https://vostride.com/docs/agent-qa/memory/serving.md)
- [How knowledge is learned](https://vostride.com/docs/agent-qa/memory/learning.md)
- [Inspect and correct](https://vostride.com/docs/agent-qa/memory/inspect.md)
- [Policies](https://vostride.com/docs/agent-qa/memory/policies.md)

### Self-improvement

- [Self-improvement](https://vostride.com/docs/agent-qa/self-improvement.md)
- [Mark a run](https://vostride.com/docs/agent-qa/self-improvement/feedback.md)
- [Self-healing](https://vostride.com/docs/agent-qa/self-improvement/healing.md)
- [Flaky tests and quarantine](https://vostride.com/docs/agent-qa/self-improvement/quarantine.md)
- [Eval corpus](https://vostride.com/docs/agent-qa/self-improvement/evals.md)

### Guides

- [Write a test](https://vostride.com/docs/agent-qa/guides/first-test.md): Describe one user journey in plain English, with checks the agent can prove or disprove on screen.
- [Web testing](https://vostride.com/docs/agent-qa/guides/web-testing.md): Point agent-qa at a web app, choose a browser, and tune timeouts, logs, accessibility checks and recordings.
- [Saved logins](https://vostride.com/docs/agent-qa/guides/auth-state.md): Sign in to a web app once, save the session, and start tests already signed in.
- [Mobile testing](https://vostride.com/docs/agent-qa/guides/mobile-testing.md): Run plain-English tests on Android and iOS apps through Appium, on emulators, simulators, real devices or BrowserStack.
- [Suites](https://vostride.com/docs/agent-qa/guides/suites.md): Group tests that run together, in order, against one target, with shared setup and settings.
- [Hooks](https://vostride.com/docs/agent-qa/guides/hooks.md): Run your own scripts before, during or after a test to prepare data, call APIs and check side effects, inside a sandbox.
- [Review a run](https://vostride.com/docs/agent-qa/guides/review-a-run.md): Find a run, see why it passed or failed, and read the evidence behind each step from the terminal, the dashboard or your coding agent.
- [Evaluate agent-qa](https://vostride.com/docs/agent-qa/guides/evaluating-agent-qa.md): Measure whether agent-qa catches real failures in your app, how stable its verdicts are, and what it costs.
- [Verify changes with your agent](https://vostride.com/docs/agent-qa/guides/coding-agent-workflow.md): The loop a coding agent follows to prove a change works in the real app, using agent-qa's tools and skills.
- [Run in CI](https://vostride.com/docs/agent-qa/guides/ci.md): Run agent-qa in a CI job, give it a model key safely, keep the evidence, and understand what happens to learning in CI.
- [Ask and chat](https://vostride.com/docs/agent-qa/guides/chat.md): Ask agent-qa to do things in plain words, one request at a time or in a conversation.

### Reference

- [CLI](https://vostride.com/docs/agent-qa/cli.md)
- [MCP server](https://vostride.com/docs/agent-qa/mcp.md)
- [Skills](https://vostride.com/docs/agent-qa/skills.md)
- [Dashboard](https://vostride.com/docs/agent-qa/dashboard.md)
- [Daemon and background work](https://vostride.com/docs/agent-qa/daemon.md)
- [Recorded test evidence](https://vostride.com/docs/agent-qa/guides/recorded-evidence.md)

### Configuration

- [Configuration](https://vostride.com/docs/agent-qa/configuration.md)
- [agent-qa.config.yaml](https://vostride.com/docs/agent-qa/configuration/global-config.md)
- [Models and credentials](https://vostride.com/docs/agent-qa/configuration/models.md)
- [Test files](https://vostride.com/docs/agent-qa/configuration/test.md)
- [Suite files](https://vostride.com/docs/agent-qa/configuration/suite.md)
- [hooks.yaml](https://vostride.com/docs/agent-qa/configuration/hook.md)
- [Variables and secrets](https://vostride.com/docs/agent-qa/configuration/env-secrets.md)
- [agent-qa.local.yaml](https://vostride.com/docs/agent-qa/configuration/local-config.md)
- [Plugins](https://vostride.com/docs/agent-qa/configuration/plugins.md)

### Migrate

- [v0.1.x to v0.2.x](https://vostride.com/docs/agent-qa/migrate/v0-1-to-v0-2.md)

## Product and workflows

- [agent-qa](https://vostride.com/index.md): Product overview, benchmark results and rankings, capabilities, and the complete documentation index.
- [AI browser testing that repairs the path, not the outcome](https://vostride.com/ai-browser-testing.md)
- [Natural language testing that is a file format, not a prompt](https://vostride.com/natural-language-testing.md)
- [Write the mobile flow once, point it at Android and iOS](https://vostride.com/ai-mobile-app-testing.md)
- [AI test automation that leaves you no script to maintain](https://vostride.com/ai-test-automation.md)
- [End-to-end tests your coding agent can write, run, and read back](https://vostride.com/e2e-testing-for-coding-agents.md)
- [Recorded demo overview](https://vostride.com/demo/agent-qa.md): Available recorded runs and links to the interactive run inspector.
- [Changelog](https://vostride.com/changelog.md): The package version behind these docs and release history.
- [Introducing agent-qa](https://vostride.com/changelog/introducing-agent-qa.md)
- [Pricing and operating costs](https://vostride.com/pricing.md): Product price, model inference, infrastructure, and license.

## QA library

- [Library index](https://vostride.com/agent-library.md): Every topic with its description. Each topic links to its recipes and guides; each recipe links back to its topic. Recipes are test designs to adapt, not recorded executions.
- [Software factory QA architecture and workflows](https://vostride.com/agent-library/software-factory.md)
- [Authentication QA recipes](https://vostride.com/agent-library/authentication.md)
- [Account recovery QA recipes](https://vostride.com/agent-library/account-recovery.md)
- [Authorization and permission QA recipes](https://vostride.com/agent-library/authorization.md)
- [Organization membership QA recipes](https://vostride.com/agent-library/organization-membership.md)
- [Billing and subscription QA recipes](https://vostride.com/agent-library/billing-subscriptions.md)
- [Checkout and payment QA recipes](https://vostride.com/agent-library/checkout-payments.md)
- [Shopping cart QA recipes](https://vostride.com/agent-library/shopping-cart.md)
- [Product catalog QA recipes](https://vostride.com/agent-library/product-catalog.md)
- [Search and filtering QA recipes](https://vostride.com/agent-library/search-filtering.md)
- [Forms and validation QA recipes](https://vostride.com/agent-library/forms-validation.md)
- [Files and media QA recipes](https://vostride.com/agent-library/files-media.md)
- [Notification QA recipes](https://vostride.com/agent-library/notifications.md)
- [Collaboration QA recipes](https://vostride.com/agent-library/collaboration.md)
- [Data table QA recipes](https://vostride.com/agent-library/data-tables.md)
- [Navigation and routing QA recipes](https://vostride.com/agent-library/navigation-routing.md)
- [Accessibility workflow QA recipes](https://vostride.com/agent-library/accessibility-flows.md)
- [Android application QA recipes](https://vostride.com/agent-library/android-flows.md)
- [iOS application QA recipes](https://vostride.com/agent-library/ios-flows.md)
- [Network recovery QA recipes](https://vostride.com/agent-library/network-recovery.md)
- [Localization QA recipes](https://vostride.com/agent-library/localization.md)
- [Scheduling and calendar QA recipes](https://vostride.com/agent-library/scheduling.md)
- [Reporting and export QA recipes](https://vostride.com/agent-library/reporting-exports.md)
- [Integration and synchronization QA recipes](https://vostride.com/agent-library/integrations-sync.md)
- [Release regression QA recipes](https://vostride.com/agent-library/release-regression.md)

## Comparisons

- [Compare testing tools](https://vostride.com/product-comparison.md): Choose by testing layer, workflow, execution model, and evidence needs; describes every comparison below.
- [agent-qa vs Midscene.js](https://vostride.com/product-comparison/agent-qa-vs-midscene.md)
- [agent-qa vs Browser Use](https://vostride.com/product-comparison/agent-qa-vs-browser-use.md)
- [agent-qa vs QA Use](https://vostride.com/product-comparison/agent-qa-vs-qa-use.md)
- [agent-qa vs Browser Use QA Use](https://vostride.com/product-comparison/agent-qa-vs-browser-use-qa-use.md)
- [agent-qa vs Stagehand](https://vostride.com/product-comparison/agent-qa-vs-stagehand.md)
- [agent-qa vs Skyvern](https://vostride.com/product-comparison/agent-qa-vs-skyvern.md)
- [agent-qa vs Puppeteer](https://vostride.com/product-comparison/agent-qa-vs-puppeteer.md)
- [agent-qa vs TesterArmy](https://vostride.com/product-comparison/agent-qa-vs-tester-army.md)
- [agent-qa vs TesterArmy e2e](https://vostride.com/product-comparison/agent-qa-vs-tester-army-e2e.md)
- [agent-qa vs Argent](https://vostride.com/product-comparison/agent-qa-vs-argent.md)
- [agent-qa vs agent-device](https://vostride.com/product-comparison/agent-qa-vs-agent-device.md)
- [agent-qa vs Momentic](https://vostride.com/product-comparison/agent-qa-vs-momentic.md)
- [agent-qa vs mabl](https://vostride.com/product-comparison/agent-qa-vs-mabl.md)
- [agent-qa vs testRigor](https://vostride.com/product-comparison/agent-qa-vs-testrigor.md)
- [agent-qa vs Autonoma](https://vostride.com/product-comparison/agent-qa-vs-autonoma.md)
- [agent-qa vs Octomind](https://vostride.com/product-comparison/agent-qa-vs-octomind.md)
- [agent-qa vs Autosana](https://vostride.com/product-comparison/agent-qa-vs-autosana.md)
- [agent-qa vs SpurTest](https://vostride.com/product-comparison/agent-qa-vs-spur.md)
- [agent-qa vs Bug0](https://vostride.com/product-comparison/agent-qa-vs-bug0.md)
- [agent-qa vs TestSprite](https://vostride.com/product-comparison/agent-qa-vs-testsprite.md)
- [agent-qa vs BaseRock](https://vostride.com/product-comparison/agent-qa-vs-baserock.md)
- [agent-qa vs QA Wolf](https://vostride.com/product-comparison/agent-qa-vs-qawolf.md)
- [agent-qa vs Katalon](https://vostride.com/product-comparison/agent-qa-vs-katalon.md)
- [agent-qa vs Functionize](https://vostride.com/product-comparison/agent-qa-vs-functionize.md)
- [agent-qa vs Tricentis](https://vostride.com/product-comparison/agent-qa-vs-tricentis.md)
- [agent-qa vs LambdaTest](https://vostride.com/product-comparison/agent-qa-vs-lambdatest.md)
- [agent-qa vs Applitools](https://vostride.com/product-comparison/agent-qa-vs-applitools.md)
- [agent-qa vs Rainforest QA](https://vostride.com/product-comparison/agent-qa-vs-rainforestqa.md)
- [agent-qa vs Autify](https://vostride.com/product-comparison/agent-qa-vs-autify.md)
- [agent-qa vs ACCELQ](https://vostride.com/product-comparison/agent-qa-vs-accelq.md)
- [agent-qa vs MagicPod](https://vostride.com/product-comparison/agent-qa-vs-magicpod.md)
- [agent-qa vs Playwright](https://vostride.com/product-comparison/agent-qa-vs-playwright.md)
- [agent-qa vs Cypress](https://vostride.com/product-comparison/agent-qa-vs-cypress.md)
- [agent-qa vs Selenium](https://vostride.com/product-comparison/agent-qa-vs-selenium.md)
- [agent-qa vs Appium](https://vostride.com/product-comparison/agent-qa-vs-appium.md)
- [agent-qa vs Maestro](https://vostride.com/product-comparison/agent-qa-vs-maestro.md)

## Articles

- [All articles](https://vostride.com/blog.md): Writing on software, agents, testing, and reliability.
- [The urge to build everything](https://vostride.com/blog/the-urge-to-build-everything.md): AI makes software easier to build. Who keeps it running? On internal tools, the SaaS-pocalypse, and choosing what your company should spend its time building.
- [agent-qa and the Fair Future](https://vostride.com/blog/agent-qa-and-the-fair-future.md): Why we believe the future of software belongs to collaborating agents, why we are building the independent verification layer, and why agent-qa is Fair Source.

## Public tools and discovery

- [Documentation MCP](https://vostride.com/docs/agent-qa/mcp.md): Streamable HTTP at `https://vostride.com/mcp` (POST, no authentication); tools `search_vostride_content`, `search_agent_qa_docs`, `search_agent_qa_library`, and `read_agent_qa_page`.
- [Site content catalogue](https://vostride.com/api/content): Search published page metadata with `query`, filter by `section`, or browse with `limit` and `offset`. Results include canonical URLs, Markdown URLs and available modification dates.
- [Documentation search](https://vostride.com/api/search?query=agent%20quickstart&limit=5): Ranked results; retrieve a result's Markdown URL or use the MCP reader.
- [Documentation source](https://vostride.com/api/docs/source?path=/docs/agent-qa/agent-quickstart): The same linked Markdown as the page's direct `.md` URL.
- [Library search](https://vostride.com/api/agent-library?query=subscription&limit=5): Search metadata or paginate by topic before fetching recipes.
- [Downloadable Skills](https://vostride.com/.well-known/agent-skills/index.json): Setup, authoring, debugging, and triage workflows with ZIP digests.
- [Agent index](https://vostride.com/.well-known/agents-index.json): Product identity, version, and onboarding interfaces.
- [MCP server card](https://vostride.com/mcp/server-card): Transport and capability metadata.
- [OpenAPI](https://vostride.com/openapi.json): Public content API reference.
- [API catalog](https://vostride.com/.well-known/api-catalog): Machine-readable service discovery.
- [Agent catalog](https://vostride.com/.well-known/ard.json): ARD catalog of the MCP server, content API and Skills; also at `/.well-known/ai-catalog.json`.
- [Content manifest](https://vostride.com/manifest.md): Product identity and every public content route.
- [Authentication guidance](https://vostride.com/auth.md): Public access and local runtime credential boundaries.

## Company

- [About](https://vostride.com/about.md): Who vostride is and what it builds.
- [Manifesto](https://vostride.com/manifesto.md): Why vostride is focused on the verification layer, building harnesses for agents and humans to ship confidently.
- [Contact](https://vostride.com/contact.md): Contact the vostride team.
- [License](https://vostride.com/license.md): The full license shipped with agent-qa.
- [Privacy](https://vostride.com/privacy.md): What vostride.com collects: no accounts or cookies, and cookieless analytics.