Stars
Rust RPC framework with high-performance and strong-extensibility for building micro-services.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…
very good whiteboard infinite canvas SDK
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.
Intelligent automation and multi-agent orchestration for Claude Code
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Hierarchical Reasoning Model Official Release
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Heavily optimized library for DEFLATE/zlib/gzip compression and decompression
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
A Lighting Pytorch Framework for Recommendation Models (PyTorch推荐算法框架), Easy-to-use and Easy-to-extend. https://datawhalechina.github.io/torch-rechub/
Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification
Build Real-Time Knowledge Graphs for AI Agents
Python tool for converting files and office documents to Markdown.
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.
Query Engine for AI - The only MCP Server you'll ever need
推荐系统入门指南，全面介绍了工业级推荐系统的理论知识（王树森推荐系统公开课-基于小红书的场景讲解工业界真实的推荐系统），如何基于TensorFlow2训练模型，如何实现高性能、高并发、高可用的Golang推理微服务。Comprehensively introduced the theory of industrial recommender system, how to trainning …
a high-performance, large-capacity, multi-tenant, data-persistent, strong data consistency based on raft, Redis-compatible elastic KV data storage system based on RocksDB
Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and m…
Official inference framework for 1-bit LLMs