Stars
Open-source, community-driven agent harness
aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR/3Embedding/3Reranker), MiniCPM(4/5), VoxCPM(0.5B/1.5/2), DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5/1.6, RMBG2.0, GLM(ASR-Nano-…
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
An experimental safe multimedia toolkit
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构…
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
An transformer based LLM. Written completely in Rust
LLMs-from-scratch项目中文翻译
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
A self-hosted Email Middleware for IMAP, SMTP, Gmail API, Graph API — built for developers
A memory-efficient patricia tree implementation written in Rust
Turso is an in-process SQL database, compatible with SQLite.
手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
High performance Rust stream processing engine seamlessly integrates AI capabilities, providing powerful real-time data processing and intelligent analysis.
DuckDB is an analytical in-process SQL database management system
Unicode validation and transcoding at billions of characters per second
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.