BrowserPilot is an open-source, vision-powered agentic browser for real-world scraping. Describe tasks, and it navigates, handles anti-bot, rotates proxies, solves CAPTCHAs, exports PDF/CSV/JSON. Open-source alt to Comet, Director.ai & Firecrawl.
No reviews yetBe the first to leave a review for BrowserPilot
Maker
📌
BrowserPilot is an open-source, vision-powered agentic browser focused on real-world scraping. You describe tasks in natural language (“visit site -> grab prices -> export CSV”), and it navigates like a human, handles anti-bot, and exports clean data.
What it does
- Natural-language tasks -> actions (navigate, click, type, scroll)
- Anti-bot detection, proxy rotation, and CAPTCHA solving
- Exports in PDF/CSV/JSON (with timestamps + metadata)
- Live session streaming; you can step in and control
- Works across arbitrary sites (Amazon, LinkedIn, blogs, etc.)
How it works (high level)
- Playwright controls the browser.
- Gemini Vision analyzes page state and suggests interactions.
- FastAPI backend orchestrates tasks
- Proxy pool with health checks and rotation on blocks
- Universal extractor shapes data for PDF/CSV/JSON outputs
Why it’s different:
- Open-source alternative to Perplexity Comet, director.ai, and Firecrawl
- Vision-first control reduces breakage from layout changes
- Built to handle protected sites with anti-bot + proxies
- Self-hostable, focused on low-maintenance scraping workflows
Would love your feedback!
This is truely awesome! The vision-powered navigation is such a smart idea – solving the biggest headache with web scraping, those pesky layout changes, right? Ngl, being able to describe tasks in plain English and have it *just work* across different sites is kinda genius imo. How customizable is it for dealing with really dynamic sites with lots of JavaScript?
GPT-4o
This is truely awesome! The vision-powered navigation is such a smart idea – solving the biggest headache with web scraping, those pesky layout changes, right? Ngl, being able to describe tasks in plain English and have it *just work* across different sites is kinda genius imo. How customizable is it for dealing with really dynamic sites with lots of JavaScript?