Stars
Democratizing Reinforcement Learning for LLMs
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
这是一个用于显示当前网速、CPU及内存利用率的桌面悬浮窗软件，并支持任务栏显示，支持更换皮肤。
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Alfred Youdao Translate Workflow
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
High performance self-hosted photo and video management solution.
Datawhale成员整理的面经，内容包括机器学习，CV，NLP，推荐，开发等，欢迎大家star
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A scalable, distributed, collaborative, document-graph database, for the realtime web
A high-performance proxy pool system based on Go, supporting automatic crawling, verification and providing proxy services. 一个基于 Go 的高性能代理池系统，支持自动抓取、验证和提供代理服务。
An open-source RAG-based tool for chatting with your documents.
Get your documents ready for gen AI
Anthropic's educational courses
OCR, layout analysis, reading order, table recognition in 90+ languages
DSPy: The framework for programming—not prompting—language models
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Tesseract Open Source OCR Engine (main repository)
Flexible concrete Error type built on std::error::Error
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。