---
title: "Your AI QA engineer"
description: "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."
canonical_url: "https://vostride.com/"
md_url: "https://vostride.com/index.md"
last_updated: "2026-10-17T01:23:35+05:30"
---

> [Documentation index](https://vostride.com/docs.md) · [Site index](https://vostride.com/llms.txt)
> Follow the Markdown links to read individual pages; the indexes list the available documentation.

# 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 is a source-available, self-improving AI testing agent built by vostride. Run plain-English YAML tests across web, Android, and iOS, locally, in CI, or through coding agents. Tests, evidence, cache, and persistent memory stay in your repository.

memidex retains useful product knowledge across runs. The self-improvement loop checks proposed lessons before applying them and retires outdated knowledge. These updates remain files you can review and revert.

There is no paid tier, hosted lock-in, seat fee, or required model vendor. Teams provide their own model credentials and execution infrastructure.

## Benchmark results and rankings

agent-qa by vostride publishes mobile agent benchmark results with task-level evidence:

| Benchmark | agent-qa result | Ranking and comparison |
| --- | --- | --- |
| [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. |

AndroidWorld used gpt-6-sol and the benchmark's own evaluators. Pass@1 counts first attempts. [Every task's actions, screenshots and verdict](https://vostride.com/benchmark/android-world.md#runs) are published.

AppControlBench used gpt-6-sol with a gpt-6-sol (high) vision judge. Completion awards 1 point for success, 0.5 for partial and 0 for failure; it is distinct from full-success pass rate. agent-qa's results are self-published and are not entries on the official AppControlBench leaderboard. Models, judges and OS versions differ between comparisons. [Methodology and run evidence](https://vostride.com/benchmark/app-control-bench.md#appcontrolbench) document the Android port and the iOS low-battery rerun.

Benchmark runs disabled memidex and self-improvement, starting each task with empty memory. These results 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

- [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md)
- [Complete setup prompt](https://vostride.com/agent-setup.txt)
- [Verify a change with your coding agent](https://vostride.com/docs/agent-qa/guides/coding-agent-workflow.md)
- [Recorded test evidence](https://vostride.com/docs/agent-qa/guides/recorded-evidence.md)
- [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md)
- [Documentation](https://vostride.com/docs/agent-qa.md)
- [Software factory QA library](https://vostride.com/agent-library.md)
- [Live demo](https://vostride.com/demo/agent-qa.md)
- [Source repository](https://github.com/vostride/agent-qa)
- [npm package](https://www.npmjs.com/package/agent-qa)

```bash
npm install -D agent-qa
npx agent-qa init --platform web
# Configure a model and target using the agent quickstart, then create and run a real test.
```

## Core capabilities

## Agentic Testing

Write tests in plain language. agent-qa runs them, adapts when your UI changes, and verifies the same expected outcome.

[Read the documentation](https://vostride.com/docs/agent-qa/guides/first-test.md)

## Product knowledge that stays with your tests.

memidex keeps persistent memory as reviewable files beside your tests, ready for future runs.

[Read the documentation](https://vostride.com/docs/agent-qa/memory.md)

## Test web, Android, and iOS with one flow

Run the same natural-language flow across web, Android, and iOS with Playwright or Appium.

[Read the documentation](https://vostride.com/docs/agent-qa/guides/mobile-testing.md)

## Built for humans and agents

Humans and agents author the same reviewable YAML, backed by your repository, skills, and MCP.

[Read the documentation](https://vostride.com/docs/agent-qa/humans-and-agents.md)

## Every validated lesson can improve the next run.

agent-qa checks proposed lessons before applying them and retires outdated knowledge. Updates stay in files you can review and revert.

[Read the documentation](https://vostride.com/docs/agent-qa/memory/curator.md)

## Self-healing test execution

When an action fails, agent-qa re-observes the screen and finds another route to the same outcome.

[Read the documentation](https://vostride.com/docs/agent-qa/self-healing.md)

## Work it out once, not every run

Reuse validated actions while the screen still matches, cutting tokens and runtime without generating scripts.

[Read the documentation](https://vostride.com/docs/agent-qa/caching.md)

## Everything it knows is a file in your repository

Tests, knowledge, and rules stay as reviewable files shared by teammates, agents, and CI.

[Read the documentation](https://vostride.com/docs/agent-qa/configuration.md)

## Run sandboxed hooks during tests

Run Node, Bun, Python, or Bash hooks in isolated containers and pass structured results back into the test.

[Read the documentation](https://vostride.com/docs/agent-qa/guides/hooks.md)

## Bring your own LLM

Switch providers, endpoints, or models in config without rewriting a single test.

[Read the documentation](https://vostride.com/docs/agent-qa/configuration/global-config.md)

## Interfaces for agents

- **CLI:** initialize, validate, run, inspect, and maintain agent-qa workspaces.
- **MCP:** expose authoring, execution, artifacts, and failure classification to MCP-capable coding agents.
- **Skills:** install reusable setup, authoring, result-triage, and debug-fix workflows.

The public documentation MCP at https://vostride.com/mcp offers search, Markdown retrieval, and the `setup_agent_qa` prompt. Test execution uses the installed local CLI or local MCP server.

See [MCP documentation](https://vostride.com/docs/agent-qa/mcp.md) and [Skills documentation](https://vostride.com/docs/agent-qa/skills.md).

## All documentation

### Overview

- [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.
- [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md): Give your coding agent a complete path from an existing repository to a verified end-to-end test.
- [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md): Install agent-qa, prepare web and mobile runtimes, connect an LLM, and inspect your first run from the dashboard or CLI.
- [Built for humans and agents](https://vostride.com/docs/agent-qa/humans-and-agents.md): Humans and coding agents author the same reviewable tests, backed by your repository, skills, and MCP.
- [Self-healing execution](https://vostride.com/docs/agent-qa/self-healing.md): Recover from a failed action by finding another route to the same expected outcome.
- [Memory overview](https://vostride.com/docs/agent-qa/memory.md): Understand agent-qa memory as file-backed behavioral observations that make future runs more product-aware without replacing live evidence.
- [Caching](https://vostride.com/docs/agent-qa/caching.md): Understand how agent-qa caches action plans, builds cache keys, invalidates stale entries, and can make similar subsequent runs 5x faster with 60% less token usage.
- [Configuration](https://vostride.com/docs/agent-qa/configuration.md): Understand the file-backed configuration system that powers agent-qa projects.
- [CLI](https://vostride.com/docs/agent-qa/cli.md): Source-backed reference for the agent-qa command line, grouped by setup, execution, authoring, configuration, maintenance, and AI-native workflows.
- [MCP](https://vostride.com/docs/agent-qa/mcp.md): Use agent-qa MCP tools to discover project context, author tests and suites, enqueue runs, inspect artifacts, and classify failures from an AI agent.
- [Skills](https://vostride.com/docs/agent-qa/skills.md): Practical guide to packaged agent-qa skills and the CLI command that lists them for AI agents.

### Guides

- [Coding-agent verification loop](https://vostride.com/docs/agent-qa/guides/coding-agent-workflow.md): Turn a code change into a tested user journey, an evidence-backed diagnosis, and a focused rerun.
- [Evaluate agent-qa on your app](https://vostride.com/docs/agent-qa/guides/evaluating-agent-qa.md): Measure useful bug detection, repeated-run cost, and agent setup success with a reproducible experiment.
- [Recorded test evidence](https://vostride.com/docs/agent-qa/guides/recorded-evidence.md): Inspect the recorded web and Android test results behind the agent-qa demo.
- [Write your first test](https://vostride.com/docs/agent-qa/guides/first-test.md): Create a source-grounded agent-qa test file with a target, context, optional hooks, per-test overrides, and natural-language steps.
- [Web testing](https://vostride.com/docs/agent-qa/guides/web-testing.md): Configure web targets and browser overrides for agent-qa tests that run through Playwright-managed Chromium, Firefox, or WebKit.
- [Auth state](https://vostride.com/docs/agent-qa/guides/auth-state.md): Capture a named web login once, reuse it across tests and suites, and pass the active Playwright storage-state JSON to hooks without exposing credential material elsewhere.
- [Mobile testing](https://vostride.com/docs/agent-qa/guides/mobile-testing.md): Configure native Android and iOS targets, local or BrowserStack devices, app installs, and required mobile app-state behavior.
- [Suites](https://vostride.com/docs/agent-qa/guides/suites.md): Combine multiple agent-qa tests into one ordered suite with shared target, context, hooks, and run overrides.
- [Hooks](https://vostride.com/docs/agent-qa/guides/hooks.md): Write sandboxed agent-qa hooks that prepare data, verify side effects, and export runtime variables back to tests and suites.

### Dashboard

- [Dashboard](https://vostride.com/docs/agent-qa/dashboard.md): Source-backed tour of the agent-qa dashboard routes for runs, tests, hooks, suites, memory, insights, config, and queue-aware workflows.

### Memory

- [Curator](https://vostride.com/docs/agent-qa/memory/curator.md): Learn how the memory curator turns run evidence into added, confirmed, deprecated, deleted, or unchanged observations.
- [Behavioral Memory Schema](https://vostride.com/docs/agent-qa/memory/behavioral-memory-schema.md): Read and review the markdown observation files that back agent-qa behavioral memory.
- [Runtime Memory Injection](https://vostride.com/docs/agent-qa/memory/runtime-injection.md): Understand how agent-qa indexes file-backed observations and injects matching memory into individual steps.
- [Memory Reliability and Maintenance](https://vostride.com/docs/agent-qa/memory/reliability-maintenance.md): Configure memory trust, injection limits, curator locking, ablation, circuit breaker behavior, security scanning, and stale suite cleanup.

### Configuration

- [Global Config](https://vostride.com/docs/agent-qa/configuration/global-config.md): Configure workspace discovery, services, registries, plugins, analytics, and default run behavior in agent-qa.config.yaml.
- [Test](https://vostride.com/docs/agent-qa/configuration/test.md): Structure a single natural-language web test definition with target, hooks, variables, steps, and per-test run overrides.
- [Suite](https://vostride.com/docs/agent-qa/configuration/suite.md): Group multiple web tests into an ordered agent-qa suite with shared target, context, hooks, and run overrides.
- [Hook](https://vostride.com/docs/agent-qa/configuration/hook.md): Register sandboxed hooks in hooks.yaml and implement scripts that prepare web test data, verify API side effects, and export runtime variables.
- [Env & Secrets](https://vostride.com/docs/agent-qa/configuration/env-secrets.md): Use .env, .env.secrets.local, hook output, and CLI variables without leaking credentials into test files or artifacts.
- [Local config](https://vostride.com/docs/agent-qa/configuration/local-config.md): Keep machine-specific provider credentials, device bindings, and app artifact paths in agent-qa.local.yaml instead of shared project config.
- [Agent rules](https://vostride.com/docs/agent-qa/configuration/agent-rules.md): Add project-specific QA behavior rules that every agent-qa web or mobile run can read before executing steps.
- [auth.json](https://vostride.com/docs/agent-qa/configuration/auth-json.md): Understand where agent-qa stores saved LLM credentials and how to create auth.json safely for CI.