Stars
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency a…
数字底座是一款面向大型政府、企业数字化转型，基于身份认证、组织架构、岗位职务、应用系统、资源角色、数据目录、安全控制等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式，具备微服务、多租户、容器化和国产化，支持用户利用代码生成器快速构建自己的业务应用，同时可关联诸多成熟且好用的内部生态应用。
AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
Unified KV Cache Compression Methods for Auto-Regressive Models
【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’
[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
Zotero chat PDF with AI, DeepSeek, GPT 4.1, ChatGPT, Claude, Gemini, Qwen3
告警管理，事件管理，统一告警、事件平台。告警事件统一接收、告警降噪、告警去重、合并、分类、告警升降级、告警屏蔽、告警通知。
A public good tool to help users verify Safe (Gnosis Safe) transactions before signing or execution.
[ICML 2025 Spotlight] An official implementation of VideoRoPE: What Makes for Good Video Rotary Position Embedding?
The Seguro Platform Application.
Welcome to BlockSeek's official documentation. BlockSeek combines state-of-the-art AI with blockchain technology to revolutionize cryptocurrency trading and analysis.
Bounty Board is a decentralized platform designed to streamline Web3 community activities.
Orderbook PoC for the demo day at the Solana Colosseum Accelerator (This is not the Urani Protocol).
The interface allowing users to submit Solana order intents for consumption by the Urani Protocol.
Urani's first MEV agent template. It listens for batches, parses them, checks for P2P matches, and spins threads for best quotes through arbitrage in different AMMs.
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
The first open autoregressive foundational video AI model.
[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (…
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D gam…
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance