---
title: "agent-qa"
description: "The self-improving QA agent for software teams."
canonical_url: "https://vostride.com/"
md_url: "https://vostride.com/index.md"
last_updated: "2026-08-17T02:33:16+05:30"
---

# agent-qa

> The self-improving QA agent for software teams.

agent-qa is a source-available, self-improving Agentic QA harness built by Vostride. Write end-to-end tests as plain-English YAML for web, Android, and iOS; run them locally, in CI, or from coding agents; and keep tests, evidence, cache, and memory in your own repository.

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

## Start here

- [Quickstart](https://vostride.com/docs/agent-qa/quickstart)
- [Documentation](https://vostride.com/docs/agent-qa)
- [Live demo](https://vostride.com/demo/agent-qa)
- [Source repository](https://github.com/vostride/agent-qa)
- [npm package](https://www.npmjs.com/package/agent-qa)

```bash
npx agent-qa init
npx agent-qa run tests/example-pass.yaml
agent-qa dashboard --port 3470 --open
```

## Core capabilities

## Write tests in natural language

Write actions and assertions in plain English; agent-qa resolves them against the live interface.

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

## Stops rediscovering your app

Turn successful runs into reviewable, evidence-backed memory that makes every future run faster.

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

## 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)

## 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/mcp)

## Improves itself, one proved run at a time

agent-qa diagnoses each run, learns only from valid evidence, and proves every lesson before using it.

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

## 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/dashboard)

## 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)

## 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)

## 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)

## 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)

## 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 authoring, result-triage, and debug-fix workflows.

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