開源專案目錄

HKUDS

AgentSpace

★ 987

"AgentSpace: Human + Agents. One Team. One Workspace"

boogu-project

Boogu-Image

★ 987

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

Nya-Foundation

NyaProxy

★ 986

NyaProxy acts like a smart, central manager for accessing various online services (APIs) – think AI tools (like OpenAI, Gemini, Anthropic), image generators, or almost any web service that uses access keys. It helps you use these services more reliably, efficiently, and securely.

xing61

zzz-api

★ 986

企业级稳定的OpenAI、Claude、Gemini等的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持Anthropic claude的官方接口形式，支持Google gemini的官方接口形式，支持：gpt-5，sora。不需要openai Key, 不需要买openai的账号，不需要美元的银行卡，通通不用的，直接调用就行，稳定好用！！智增增

sophgo

tpu-mlir

★ 985

Machine learning compiler based on MLIR for Sophgo TPU.

neo4j-contrib

mcp-neo4j

★ 984

Neo4j Labs Model Context Protocol servers

feicaiclub

video-spec-builder

★ 984

video-spec-builder —— 把我想做个视频逼成一份精确到秒的分镜脚本 video-spec.md,交给 HyperFrames 渲染。一条命令装到 Claude Code / Cursor / Codex:npx skills add feicaiclub/video-spec-builder

pollockjj

ComfyUI-MultiGPU

★ 984

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose

OpenBMB

VisRAG

★ 983

Parsing-free RAG supported by VLMs

Qengineering

Jetson-Nano-Ubuntu-20-image

★ 983

Jetson Nano with Ubuntu 20.04 image

ReikanYsora

Helios

★ 983

Helios - Make your energy visible, in 2.5D in a Lovelace card for Home Assistant

messense

jieba-rs

★ 982

The Jieba Chinese Word Segmentation Implemented in Rust

XYZ-AI-Lab

axrl

★ 981

AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.

Merserk

dlss5-visual-enhancer

★ 981

DLSS 5 Neural Video & Image Enhancer with Frame Interpolation

persian-calendar

persian-calendar

★ 979

Android 波斯日曆。英文 Android 波斯日曆 一個簡單、免費和開源的 Android 日曆 專案狀態和本地化 下載 如果您的裝置運行的是舊版本的 Android，請參閱此。

xoreaxeaxeax

asm-hall-of-shame

★ 979

Racing to the bottom of CPU performance

TypingMind

typingmind

★ 978

The most advanced Web UI for AI chat

zhu1090093659

spec_driven_develop

★ 978

Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

om-ai-lab

VLX-Seek

★ 978

VLX-Seek is a device-native vision-language model that enables machines to see, understand, and reason about the visual world with high precision.

jaredrhod

barehands

★ 978

Move things on your screen with your bare hands. A webcam-powered, hand-tracked interface for your AI. No headset. No controllers.