Stars
An open protocol enabling communication and interoperability between opaque agentic applications.
YOLOv12: Attention-Centric Real-Time Object Detectors
A modern vue admin panel built with Vue3, Shadcn UI, Vite, TypeScript, and Monorepo. It's fast!
这是一个前后端分离的中台、后台，后端基于go、go-kratos、ent、gorm等，前端基于vue3、ts、Antdv、Vben开发。支持多租户、数据权限、动态Api、任务调度、OSS文件上传、滑块拼图验证、国内外主流数据库自由切换和动态高级查询。集成统一认证授权、事件总线、国际化、数据验证、分布式缓存、分布式事务、Ip限流、全Api鉴权、集成测试、性能分析、健康检查、接口文档等。
全面ESM+Vue3+Vite+Element-Plus+TypeScript编写的一款后台管理系统（兼容移动端）
Effortless data labeling with AI support from Segment Anything and other awesome models.
🎉 (RuoYi-Go) 前端基于RuoYi-Vue3，后端用Go(Go+Iris+Gorm)编写的权限管理系统，用DDD领域驱动设计(六边形架构)实现
FlashMLA: Efficient MLA decoding kernels
Integrate the DeepSeek API into popular softwares
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
SGLang is a fast serving framework for large language models and vision language models.
Janus-Series: Unified Multimodal Understanding and Generation Models
💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A high-throughput and memory-efficient inference and serving engine for LLMs
Open-source high-performance RISC-V processor
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
Refine high-quality datasets and visual AI models
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.
Cross-platform, customizable ML solutions for live and streaming media.