What is agent-qa
Write tests in natural language for web and mobile. agent-qa learns from past runs, adapts to UI changes, and catches regressions before you ship.
Overview
agent-qa: The self-improving Agentic QA harness with Memory. Write tests in natural language for web and mobile. agent-qa learns from past runs, adapts to UI changes, and catches regressions before you ship.
Quickstart
Install agent-qa, initialize the workspace, validate the generated files, and run the first local QA workflow.
Explore demos
Open curated agent-qa runs in the interactive demo viewer and inspect how real test steps execute.
Configuration
Review the file-backed configuration system for global settings, tests, suites, hooks, variables, secrets, devices, rules, and auth.
Memory
Review how file-backed product, suite, and test observations make future runs more product-aware.
Caching
Reuse cached action plans for similar subsequent runs, with landing-page examples showing 5x faster execution and 3x fewer planner tokens.
Tests
Write one plain-English YAML journey with stable intent, reviewable steps, and source-controlled expectations.
Web Testing
Run browser flows against local or staged web apps without hardcoded selectors or fragile DOM coupling.
Auth state
Capture a named web login once, reuse it by logical name, pass the active state to hooks, and keep credential material out of artifacts.
Suites
Bundle related tests, targets, configuration, and hooks into repeatable workflows for a feature area.
Mobile Testing
Use the same natural-language workflow model for mobile app journeys while preserving artifacts locally.
Hooks
Prepare data, call project scripts, verify side effects, and clean up state before or after a run.
How agent-qa works
Write tests in natural language
Describe the user journey in plain English: what to open, what to do, and what to assert. agent-qa turns that intent into repeatable execution.
Bring your own LLM
Use any hosted or local model. It also works with Codex and Claude Code subscriptions.
Run tests
Run tests from either the dashboard or the CLI. Group multiple tests into a suite to execute user journeys end-to-end.
Generate memory and context
Each run passes through a memory curator that records product behavior, test intent, and suite context, then creates contextual memory for future test runs.
Improve the next run
Future executions use the evolved agent context. That memory helps the agent adapt to product changes at runtime, recover from brittle UI drift, and become more reliable over time.
Grow a product-aware QA agent
The end state is a QA agent with enough context about your product to author tests, run them, inspect failures, and keep improving the testing loop.