Jan is an open-source desktop application built around running large models offline on your own computer, maintained by the Menlo Research team, and a...
OpenCode is worth installing, provided you are willing to configure models yourself and pay the bills yourself. For developers who do not want to be t...
MinerU is hard to avoid in document parsing these days: it converts layout-heavy PDFs into clean Markdown or JSON, turns formulas into LaTeX and table...
Tabby is often the first name teams look at when they want a coding assistant whose code never leaves the internal network. It is a self-hosted AI cod...
Docling tackles the most underestimated hurdle before feeding PDFs to a large model: layout. Ordinary extractors dump a PDF in character order, so two...
Crawl4AI is an open-source Python library that turns web pages into clean Markdown, tackling the dirty step before web content reaches a large model: ...
Khoj has a clear ambition: turn the documents, notes and web pages scattered across your computer into a personal knowledge base you can simply ask qu...
LibreChat brings model entry points scattered across providers into a single interface, solving the problem of repeatedly switching between web pages,...
