SerpApi

–

Easily scrape Google and other search engines with SerpApi.

This listing is not live yet. It will be published on July 31, 2026. Publish sooner — every option below includes fast publishing.

Skip the queue

$49

one-time payment

Publishes within 3 business days
No recurring billing

Bronze

$59/mo

billed monthly

1x impression weight

Skip the queue
Featured on the homepage
Starred at the top of your category

Silver

$99/mo

billed monthly

1.5x impression weight

Everything in Bronze
Featured in our GitHub README
Your logo on every listing page

Gold

Best ROI

$179/mo

billed monthly

10x impression weight

Everything in Silver
Featured in every newsletter issue
Top banner across the site
Ad card on every category page
Ad card on every listing page

agent-qa

AI/Testing/Tooling

Visit website

Self-improving QA agent for web and mobile apps with natural-language tests, run memory, UI-change adaptation, and regression detection before shipping.

About agent-qa

agent-qa is an open-source QA test harness that lets developers write tests in natural language for web and mobile applications. Tests are defined as actions and assertions in plain language, and the agent executes them by working from visible UI roles, labels, and screen state rather than fixed selectors. When a sub-action such as a click, fill, or select fails during a run, the system re-observes the UI and attempts a different path, allowing tests to recover from UI drift or flaky interactions within the same run.

The tool builds execution memory from product, suite, and test observations across runs, and incorporates context from previously healed steps to inform future test executions. An action cache reuses validated plans across similar subsequent runs to reduce planner work, token usage, and runtime overhead. Tests, configurations, hooks, memory, and suite logic are stored as version-controlled code, allowing them to be diffed, reviewed, and shared across teams.

It provides a dashboard and CLI for developers, along with MCP support and skills for coding agents. It supports running Node, Bun, Python, or Bash hooks in isolated Docker containers for tasks like environment setup, API calls, fixture seeding, and state teardown. It can be run with a choice of LLM backend, including OpenAI- and Anthropic-compatible endpoints, Gemini, local or open-source models, or subscriptions such as Codex and Claude Code. It is installed as an npm package and is intended for software teams building automated end-to-end tests for web and mobile products.

Key features

Write tests in natural language for web and mobile apps
Self-healing test execution that re-observes the UI and retries on failure
Self-improves over time by building execution memory from past runs
Action cache reuses validated plans to reduce token usage and runtime
Runs sandboxed Node, Bun, Python, or Bash hooks in isolated Docker containers
Bring your own LLM via OpenAI- and Anthropic-compatible endpoints, Gemini, or local models

Frequently asked questions

Is agent-qa open source?

Yes, agent-qa is open source and tests, configs, hooks, memory, and suite logic all live as version-controlled code.

What platforms does it support testing on?

It supports writing tests in natural language for both web and mobile.

Which LLMs can I use with agent-qa?

You can run tests with OpenAI- and Anthropic-compatible endpoints, Gemini, local or open-source models, and subscriptions like Codex and Claude Code.

How do I install and get started?

Install it with npm install -D agent-qa, then run npx agent-qa init followed by npx agent-qa dashboard --open.

Does it require Docker?

Docker is required for running hooks, since agent-qa executes Node, Bun, Python, and Bash hooks in sandboxed Docker containers.

Advertise here