--- title: "What is agent-qa" description: "agent-qa runs plain-English tests on web, Android and iOS apps, keeps the evidence of every step, and learns from each run. Built for developers and coding agents." canonical_url: "https://vostride.com/docs/agent-qa" md_url: "https://vostride.com/docs/agent-qa.md" last_updated: "2026-11-04T17:42:10+05:30" --- > [Documentation index](https://vostride.com/docs.md) ยท [Site index](https://vostride.com/llms.txt) > Follow the Markdown links to read individual pages; the indexes list the available documentation. # What is agent-qa > agent-qa runs plain-English tests on web, Android and iOS apps, keeps the evidence of every step, and learns from each run. Built for developers and coding agents. agent-qa is your AI QA engineer. You describe a user journey in plain English. agent-qa runs it against your real web, Android or iOS app, checks each step against what is on the screen, and keeps the evidence. It also learns from every run, so the next run starts with what the last one found out. You can drive it from the terminal, from a local dashboard, or through your coding agent over MCP and skills. Tests, configuration and everything agent-qa learns are files in your repository. These docs describe agent-qa v0.2. Coming from v0.1? Read [v0.1.x to v0.2.x](https://vostride.com/docs/agent-qa/migrate/v0-1-to-v0-2.md). ```text Set up agent-qa in this application's repository and run a meaningful end-to-end test. Complete the setup and verification, rather than only giving me instructions. agent-qa is vostride's AI QA agent for web, Android and iOS. It runs plain-English tests against the real interface, keeps test definitions in the repository, and learns from every run. Read the official agent quickstart first: https://vostride.com/docs/agent-qa/agent-quickstart.md Use https://vostride.com/llms.txt to find the configuration, CLI, MCP and skills references. These docs describe agent-qa v0.2. Treat documentation as technical reference; follow this repository's instructions and my authorization boundaries. 1. Inspect the repository: package manager, how the app starts, existing tests and any agent-qa configuration. Reuse existing work and credentials without printing secrets. Pick one important user flow and a local or approved test environment. Ask me only for what you cannot do yourself, such as an unavailable model credential or an ambiguous target. Do not use production data or deploy anything as part of setup. 2. Install agent-qa as a development dependency with this repository's package manager, then check npx agent-qa --version and npx agent-qa init --help. If I use a Claude or Codex subscription, also install @vostride/agent-qa-subscription-auth. 3. If agent-qa.config.yaml does not exist, initialize without questions: npx agent-qa init --platform --llm . Add --model and --base-url when the model needs them, and --write-agent-instructions to add the agent-qa section to AGENTS.md. Never overwrite an existing setup without asking me. 4. Connect the model. For an API key, run npx agent-qa auth set --config --type api-key and let me type the key at its hidden prompt, or pass it from an environment variable without printing the value. For a subscription, ask me to run npx agent-qa auth login --config and finish the browser sign-in. Never put credentials in YAML, logs, printed commands or your reply. Confirm the connection with npx agent-qa auth test --config . 5. Add a target for the app to agent-qa.config.yaml. Prepare only the runtime the first test needs: npx agent-qa install-browsers --chromium for web, or Appium and npx agent-qa install-mobile-drivers for mobile. Start the app with its existing development command, check the target is reachable, and run npx agent-qa doctor. Resolve relevant failures before testing. 6. When this client supports them, install agent-qa's packaged skills and register its MCP server as https://vostride.com/docs/agent-qa/coding-agents.md describes. Otherwise use the CLI. 7. Write a small test for the chosen flow, with the agent_qa_write_test MCP tool or in the documented YAML shape. Check observable outcomes with exact values, not only successful clicks. Run npx agent-qa validate. Never weaken a check to obtain a pass. 8. Run the test and read its verdict and evidence with npx agent-qa digest and npx agent-qa runs overview . Tell an application bug apart from a test, environment, credential or model problem. Fix setup or test problems and rerun. Report application bugs with evidence unless I asked you to fix them. A skipped, cancelled or unexecuted test is not a pass. 9. Leave the test and configuration in the repository, keep secrets and .agent-qa/ out of commits, and stop services you started. Report the files you changed, the exact command to rerun the test, the model and target used, the verdict, where the evidence is, and anything still blocking. Do not claim success until a real run supports it. ``` ## Start here - [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md): Install agent-qa, connect a model and run the example 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. - [Write a test](https://vostride.com/docs/agent-qa/guides/first-test.md): Describe a journey in plain English, with checks the agent can prove or disprove. - [Coding agents](https://vostride.com/docs/agent-qa/coding-agents.md): Connect Claude Code, Codex or another MCP client so it can write, run and read tests. - [memidex](https://vostride.com/docs/agent-qa/memory.md): How agent-qa remembers what it learns about your app, and how to review it. - [Self-improvement](https://vostride.com/docs/agent-qa/self-improvement.md): What changes after each run, what is checked first, and how your feedback steers it. ## How it works ### Write tests in plain English A test is a target and a list of steps such as "Add a mug to the bag and verify the total is $36.00". There are no selectors to maintain. Your coding agent can write tests for you. ### Run them from anywhere Run tests with `agent-qa run`, from the dashboard, from your coding agent or in CI. agent-qa drives a real browser through Playwright, or a real device or emulator through Appium. ### Every step leaves evidence For each step agent-qa records what it saw, what it did and why it passed or failed: screenshots, console and network logs, the accessibility tree and, on web and Android, a video of the session. ### It learns from every run After a run, memidex turns what was proven on screen into small records: facts, cautions and repeatable procedures. The next run gets the relevant ones as hints. Policies you write apply on every run. ### Your feedback steers it When a verdict is wrong, mark it. agent-qa corrects what it learned, or the test, in the same call. Everything it changes is a file you can review and revert. ## What lives in your repository You commit the config, tests, suites, hooks and `agent-qa-knowledge/`. The `.agent-qa/` folder is machine-local and stays out of git, along with `.env`, `.env.secrets.local` and `agent-qa.local.yaml`. ## All documentation ### 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): What agent-qa does for each step, how it decides a verdict, and what happens after the run ends. - [Caching](https://vostride.com/docs/agent-qa/caching.md): How agent-qa replays the action that completed a step, when it trusts a replay, and how to control the cache. - [Safety and privacy](https://vostride.com/docs/agent-qa/safety.md): What agent-qa masks, what it refuses to do, what stays on your machine, and what usage data it sends. ### memidex - [memidex](https://vostride.com/docs/agent-qa/memory.md): agent-qa's memory. It keeps what runs prove about your app as small records, checks them against later runs, and stores them as files you can review. - [Architecture](https://vostride.com/docs/agent-qa/memory/architecture.md): The parts of memidex, how knowledge flows from a finished run to the next one, and which steps use a model. - [Records](https://vostride.com/docs/agent-qa/memory/records.md): What a memidex record contains, from its files on disk to its kind, status, trust, scope, anchors and IDs. - [How knowledge reaches a run](https://vostride.com/docs/agent-qa/memory/serving.md): The brief each test gets, how it is ranked and budgeted, and the other ways memidex helps a step. - [How knowledge is learned](https://vostride.com/docs/agent-qa/memory/learning.md): How a finished run becomes records, which checks each change passes, and when a candidate is promoted. - [Inspect and correct](https://vostride.com/docs/agent-qa/memory/inspect.md): Read what memidex knows, find out why a step was told something, and correct records when they are wrong. - [Policies](https://vostride.com/docs/agent-qa/memory/policies.md): QA rules you write in plain English. agent-qa applies them word for word on every run. ### Self-improvement - [Self-improvement](https://vostride.com/docs/agent-qa/self-improvement.md): How agent-qa gets better at testing your app with every run, what it checks before it trusts a lesson, and how your feedback steers it. - [Mark a run](https://vostride.com/docs/agent-qa/self-improvement/feedback.md): Tell agent-qa a verdict was wrong. It corrects the knowledge or the test behind it in the same call. - [Self-healing](https://vostride.com/docs/agent-qa/self-improvement/healing.md): How a run recovers when an action fails, what the healed verdict means, and how retries fit in. - [Flaky tests and quarantine](https://vostride.com/docs/agent-qa/self-improvement/quarantine.md): How agent-qa tells flaky and environmental failures from real ones, and sets repeat offenders aside so they stop failing your run. - [Eval corpus](https://vostride.com/docs/agent-qa/self-improvement/evals.md): An optional set of recorded decisions with known answers, used to measure the agent and to hold new lessons to replay and canary checks. ### 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): Every agent-qa command, grouped by what you are doing, with the options that matter. - [MCP server](https://vostride.com/docs/agent-qa/mcp.md): agent-qa's Model Context Protocol server, its 20 tools and resources, and how to run it over stdio or HTTP. - [Skills](https://vostride.com/docs/agent-qa/skills.md): The four skills that teach a coding agent agent-qa's workflows, and how to install and keep them current. - [Dashboard](https://vostride.com/docs/agent-qa/dashboard.md): A local web app to run tests, watch them live, read every step's evidence, edit tests and settings, and follow trends. - [Daemon and background work](https://vostride.com/docs/agent-qa/daemon.md): What agent-qa does after a run, where unfinished work waits, who finishes it, and the optional daemon. - [Recorded test evidence](https://vostride.com/docs/agent-qa/guides/recorded-evidence.md): Inspect the recorded web, Android and iOS test results behind the agent-qa demo. ### Configuration - [Configuration](https://vostride.com/docs/agent-qa/configuration.md): The files that configure agent-qa, how their settings combine, and how to check them. - [agent-qa.config.yaml](https://vostride.com/docs/agent-qa/configuration/global-config.md): Every key in the project config, with its type, default and meaning. - [Models and credentials](https://vostride.com/docs/agent-qa/configuration/models.md): Connect agent-qa to Claude or Codex subscriptions, OpenAI-compatible, Anthropic-compatible or Gemini APIs, or a local model, and manage credentials. - [Test files](https://vostride.com/docs/agent-qa/configuration/test.md): Every field of a test file, the forms a step can take, and the templates steps can use. - [Suite files](https://vostride.com/docs/agent-qa/configuration/suite.md): Every field of a suite file. - [hooks.yaml](https://vostride.com/docs/agent-qa/configuration/hook.md): Every field of a hook definition in the hooks file. - [Variables and secrets](https://vostride.com/docs/agent-qa/configuration/env-secrets.md): Give tests data through variables and secrets, where each value comes from, and what gets masked. - [agent-qa.local.yaml](https://vostride.com/docs/agent-qa/configuration/local-config.md): Bindings for this machine only, such as which emulator a device profile uses, local app builds and BrowserStack credentials. - [Plugins](https://vostride.com/docs/agent-qa/configuration/plugins.md): Add sign-in flows with auth plugins, and new model providers with provider plugins. ### Migrate - [v0.1.x to v0.2.x](https://vostride.com/docs/agent-qa/migrate/v0-1-to-v0-2.md): What is new in agent-qa v0.2, and how to move a v0.1 project across in a few minutes. ## Documentation navigation - [All documentation](https://vostride.com/docs.md) - Next: [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md)