SiluPanda/agent-crawl

High performance, lightweight and typesafe library to crawl and scrape web, built for LLM agents.

34
/ 100
Emerging

This tool helps developers working with AI agents to efficiently gather information from websites. It takes URLs as input, intelligently scrapes web content, and delivers clean, token-optimized Markdown or structured JSON output. AI agent developers can use this to provide their agents with relevant, noise-free web data for tasks like summarization, question answering, or data extraction.

Available on npm.

Use this if you are building AI agents and need a reliable, high-performance way to fetch web content and process it into a clean, token-efficient format ready for an LLM's context window.

Not ideal if you are looking for a simple browser automation tool for personal use or a general-purpose web scraping solution that doesn't prioritize LLM agent integration.

AI-agent-development web-data-collection LLM-tooling content-extraction AI-workflow-automation
Maintenance 10 / 25
Adoption 4 / 25
Maturity 20 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

TypeScript

License

MIT

Category

llm-web-scraping

Last pushed

Feb 10, 2026

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/SiluPanda/agent-crawl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.