Docs ingestion
Walk documentation trees and push Markdown into your vector store on completion.
Building a RAG corpus or monitoring site? Crawl discovers pages, renders each one, and returns results via webhook when the job finishes.
Works with your agent stack
Single-page extraction is the start. Crawl follows internal links up to your depth and page limits, processing each URL through the render chain.
Walk documentation trees and push Markdown into your vector store on completion.
Capture years of posts in one async job instead of scripting pagination yourself.
Get notified when the crawl finishes so your pipeline indexes without polling.
Crawl returns a job ID immediately. Pages render in the background with the same smart chain as single-url endpoints.
Control max_depth and max_pages so crawls stay bounded on large sites.
Regex filters skip admin paths and focus on the sections you care about.
Pay per successful render. Failed pages do not burn credits.
POST seed URL with depth limits. Receive job_id.
View docs →Your server receives completion payload with URLs and extracted content.
Async mode →Chunk and embed crawl results into your vector database.
RAG use case →No. You get a job ID and results via webhook or polling when the job completes.
Yes. Use include_pattern and exclude_pattern to scope the crawl.
Configure the crawl to extract Markdown, HTML, or screenshots per page depending on your pipeline.
Thumbnail every listing. Crawl categories until the full catalog is covered.
Learn more →AI & agentsFeed your vector database with fresh, clean web content stripped of boilerplate.
Learn more →AI & agentsGive your AI agent live eyes on the web. One MCP install, ten tools.
Learn more →