Stars
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
2026最新悄咪咪收集的10000+个Telegram群合集、tg导航、电报导航、telegram导航，附全网最有趣好用的机器人BOT🤖【tg10000.com】
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your pho…
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, an…
cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台，算法全链路流程，多租户，算力租赁平台，token中转，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务，VGPU虚拟化，云边端协同，边缘计算，自动化标注平台，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindi…
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous soci…
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
Text-audio foundation model from Boson AI
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
Toolkit for linearizing PDFs for LLM datasets/training
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
CMMLU: Measuring massive multitask language understanding in Chinese
基于chatgpt-next-web，增加了midjourney绘画功能，支持mj-plus的ai换脸和局部重绘，接入了stable-diffusion，支持oss，支持接入fastgpt知识库，支持suno，支持luma。支持dall-e-3、gpt-4-vision-preview、whisper、tts等多模态模型，支持gpt-4-all，支持GPTs商店。新增加了支持后台管理的版本，…
RAGChecker: A Fine-grained Framework For Diagnosing RAG
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.