Skip to content
AgentOpen-source agent

webqa-agent

Autonomous web testing agent that checks functionality, performance, UX and security

Pricing
Open source
Platforms
CLI, Web, self-hosted
GitHub stars
240
Last commit
5 months ago
Language
Python
License
Apache-2.0

About webqa-agent

webqa-agent is an open-source agent for browser automation. It is available on CLI, Web, self-hosted and API.

WebQA Agent drops the test script: you state a goal in one sentence and it drives a browser to try it, using multimodal understanding of the page. The README describes three forms of testing, a lightweight Flash mode for quick smoke tests, a Standard Generate mode that discovers pages and plans tests (focused when you give goals, exploratory when you do not), and a Run mode that executes YAML instructions for repeatable regression checks.

It can be used from a CLI, a web dashboard, or from coding agents such as Cursor and Claude Code through MCP or a skill. For teams, a Docker Compose deployment adds a dashboard with test management and history; you supply an LLM API key in the environment file.

It is a Python project under Apache-2.0, with a Discord and WeChat community linked from the README.

What it does

Flash mode
Turns a one-sentence goal into a quick browser test.
Generate mode
Discovers the site and plans tests, either focused on goals or exploratory.
Run mode
Executes YAML steps with expected checks for regression testing.
MCP and skill access
Lets Cursor, Claude Code and similar agents trigger tests.
Docker Compose dashboard
Adds test management and run history for teams.

Good for

  • Smoke-test a new feature from inside an IDE
  • Explore a freshly built site for broken flows
  • Re-run a fixed regression checklist before release
  • Audit pages for performance and security issues

Pricing

Open source

Apache-2.0; needs your own LLM API key

webqa-agent FAQ

Do I need to write test scripts?

No, Flash and Generate modes work from a natural-language goal.

How do I run it with a dashboard?

Copy the example .env, add your LLM API key and run the start script in deploy/docker-compose.

Can coding agents call it?

Yes, through MCP or a skill, as the README describes.

Is webqa-agent free?

Yes. webqa-agent is open source, so you can use and self-host it for free.

What are the best alternatives to webqa-agent?

The closest alternatives to webqa-agent are deepseek-harness, gemini-cli, learn-claude-code, Codewhale and oh-my-pi.

Alternatives to webqa-agent

  1. Open-source agent harness from DeepSeek, built on a plugin architecture

    • Open source
    • Open-source agent
    • 282K GitHub stars
    • Multi-agent frameworks
  2. Open-source terminal agent for Gemini Code Assist workflows on Google Cloud

    • Open source
    • Open-source agent
    • 109K GitHub stars
    • AI models and LLM tooling
  3. Hands-on course teaching how to build the harness around an AI coding agent

    • Open source
    • Hosted agent
    • 80.5K GitHub stars
    • AI models and LLM tooling
  4. Terminal coding agent in Rust that works with any model and can split tasks across agents

    • Open source
    • Open-source agent
    • 41.2K GitHub stars
    • Coding
  5. Terminal coding agent with LSP, debugger access, subagents and a native Rust core

    • Open source
    • Open-source agent
    • 39.2K GitHub stars
    • Coding
  6. Terminal coding agent that talks to OpenAI, Gemini, Ollama and 200-plus other models

    • Open source
    • Open-source agent
    • 34.4K GitHub stars
    • Coding