handrew/browserpilot
Natural language browser automation
Uses GPT-3/GPT-3.5 to compile natural language instructions into Selenium-based browser automation code, with a modular action system where each capability (click, find_element, scroll, etc.) maps directly to agent methods. Integrates with OpenAI's API and Chrome/Chromedriver, plus optional memory via embeddings index (LlamaIndex) to help the agent synthesize what it observes across browsing sessions. Supports reusable function definitions and YAML/JSON instruction files to avoid repeated API calls.
628 stars. No commits in the last 6 months.
Stars
628
Forks
74
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/handrew/browserpilot"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
fmind/bromate
Web browser automation through agentic workflows.
fabriziosalmi/iamnotacoder
AI code generation and improvement
przeprogramowani/10x-test-planner
A Node-based CLI tool to generate test plans from video recordings using Google's Gemini models.
PinsaraPerera/PyTestAI
PyTestAI is a CLI tool that automatically generates pytest-compatible test cases for your Python...
Hauntlight/GAI4-TDD
GAI4-TDD (Generative Artificial Intelligence for Test-Driven Development) is a PyCharm plugin...