Repository profile
👻 Experimental library for scraping websites using OpenAI's GPT API.
Repository updates
Get generated jamesturk/scrapeghost development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-06-26 04:47
1 capture since 2026-06-26
Stars from baseline 0
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-06-26 04:47
pyproject.toml
python ecosystem,
0 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
Self-hosted webscraper.
Python scraper based on AI
An experiment to give an autonomous GPT agent access to a browser and have it accomplish tasks
Web scraping MCP server for AI agents — screenshots, content extraction, structured scraping
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
Giving ChatGPT access to a real terminal
https://jamesturk.github.io/scrapeghost/
403 Forbidden | https://api.github.com/repos/jamesturk/scrapeghost/readme | message=API rate limit exceeded for user ID 8257474. If you reach out to GitHub Support for help, please include the request ID D7FE:1B2858:1FA782C:1EDADB4:6A3E044D and timestamp 2026-06-26 04:47:09 UTC. For more on scraping GitHub and how it may affect your rights, please review our Terms of Service (https | rate_limit_remaining=0 | rate_limit_reset=1782450010
