Stars
RAGChecker: A Fine-grained Framework For Diagnosing RAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
A video translation and dubbing tool powered by LLMs, offering professional-grade translations and one-click full-process deployment. It can generate content optimized for platforms like YouTube，T…
SkyReels V1: The first and most advanced open-source human-centric video foundation model
SkyReels-V2: Infinite-length Film Generative model
Dedoc is a library (service) for automate documents parsing and bringing to a uniform format. It automatically extracts content, logical structure, tables, and meta information from textual electro…
Modern Docker Management, Designed for Everyone
A curated list of free courses with certifications. Also available at https://free-certifications.com/
An extremely fast Python package and project manager, written in Rust.
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2
Official inference library for Mistral models
Sealos is a production-ready Kubernetes distribution that makes deployment simple and efficient. Instantly set up development environments for any programming language or framework, deploy high-ava…
A typescript interactive engine, support 2D, 3D, animation, physics, built on WebGL and glTF.
The fastest way to develop full-stack web apps with React & Node.js.
File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …
Open Source Document Management System for Digital Archives (Scanned Documents)
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.