Align Anything: Training All-modality Model with Feedback

The L2 interface of the Hetu ecosystem

A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.

A Tiny structure of pytorch for learning;

OmniAgent Framework is an advanced, modular AI orchestration system that transforms Web3 development by seamlessly integrating artificial intelligence with blockchain technologies.

The interface allowing users to submit Solana order intents for consumption by the Urani Protocol.

Curated selection of technical publications on the solana blockchain, with a focus on DeFi, infrastructure, MEV, and fee (free) markets.

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。

Enterprise-grade feature flag platform that you can self-host. Get started - free.

Improving Generalist Model with Domain-Specific Experts

Source code for the paper "A Lightweight Framework for Fast Trajectory Simplification".

[CVPR2025] AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

The first open autoregressive foundational video AI model.

Source code for Spatio-Temporal Trajectory Similarity Learning in Road Networks. KDD 2022.

SSD1309 full function driver library for general MCU and Linux.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

[CVPR 2025] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

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 (…

Applications self-hosting and DevOps platform for running open source, web-based linux Panel of lite PaaS

[CVPR 25] RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain…

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

OV2640 full function driver library for general MCU and Linux.

迈特短剧系统是一款功能强大的海外短剧平台，包含H5、安卓APP、苹果APPP多种展示形式，支持PayPal支付、stripe支付，Facebook登录、游客登录、Google登录、多语言选择，提供多开的开源系统。该系统提供了丰富的短剧资源，支持用户免费观看热门短剧、影视作品，同时也支持多种付费观看方式，如单人、全款和会员等，满足不同用户的需求。

DS1302 full function driver library for general MCU and Linux.

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

A UI-Focused Agent for Windows OS Interaction.