aidriventesting/Agent
Open-source AI agent for UI automation, combining structural and visual understanding of mobile & web interfaces. Toward the next generation of open-source, AI-driven testing.
Integrates with Robot Framework as a natural-language library that converts plain-English instructions into UI actions via multi-provider LLMs (OpenAI, Claude, Gemini). Uses vision-based UI parsing with OmniParser and Set-of-Mark techniques to ground visual elements, supporting both mobile (via Appium) and web platforms through a unified LLM→context→tool selection pipeline. Keywords like `Agent.Do`, `Agent.Check`, and `Agent.Ask` enable semantic test steps without explicit selectors or coordinates.
Stars
11
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jan 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/aidriventesting/Agent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
browserwing/browserwing
BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to...
theredsix/cerebellum
Browser automation system that uses AI-driven planning to navigate web pages and perform goals.
MigoXLab/webqa-agent
Autonomous web browser agent that audits performance, functionality & UX for engineers and...
nottelabs/notte
🌸 Best framework to build web agents, and deploy serverless web automation functions on reliable...
hyperbrowserai/HyperAgent
AI Browser Automation