Web scraping in .NET has always meant gluing together an HTTP client, an HTML parser, a queue, and a storage layer, then babysitting selectors that break the moment a site ships a redesign. WebReaper collapses that into one declarative, parallel pipeline, and adds an AI layer on top.

What makes it different

Drop on PATH, run. A ~12 MB native binary. No Docker, no Postgres, no signup.
AI-native by composition. Markdown by default; add schema extraction, an LLM fallback, self-healing selectors, or an autonomous agent with one .With… call.
Bring any LLM. OpenAI, Anthropic, Ollama, Azure OpenAI, llamafile, via Microsoft.Extensions.AI.
MIT, not AGPL. Embed it in commercial software without license friction.

Read the getting started guide to try it.