GitHub repo leaderboard by stars, growth rate and activity.

• opendatalab

  #1opendatalab/MinerU-HTML

  MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

  Python288 starslast pushed 6 months ago
• vakovalskii

  #2vakovalskii/searcharvester

  Self-hosted search + markdown harvester for AI agents. SearXNG (100+ engines) + FastAPI + trafilatura. Tavily-compatible /search plus /extract with size presets and pagination. One-command Docker Compose.

  Python262 starslast pushed 5 months ago

#	Repo	Language	Stars	30-day trend	Last updated
1	opendatalab opendatalab/MinerU-HTML MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.	Python	288		last pushed 6 months ago
2	vakovalskii vakovalskii/searcharvester Self-hosted search + markdown harvester for AI agents. SearXNG (100+ engines) + FastAPI + trafilatura. Tavily-compatible /search plus /extract with size presets and pagination. One-command Docker Compose.	Python	262		last pushed 5 months ago

All · 11,658