仓库/Skill 库

用于高性能 AI 模型服务（vLLM、SGLang）和按需 SSH 访问 GPU 实例的 GPU 集群管理器。A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

LLM 实战指南：从基础到使用 LLMOps 最佳实践将 LLM 和 RAG 应用部署到 AWSThe LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

🏝️ OASIS：基于一百万 Agent 的开放社交交互仿真。🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.

面向常驻 Agent 的开源个人云操作系统。Open-Source Personal Cloud OS for Always-On Agents

面向 monorepo 的终极 RAG。借助 AI 与知识图谱的能力，对多语言代码库进行查询、理解与编辑。The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场，支持国产cpu/gpu/npu 昇腾生态，支持RDMA，支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano等分布式

从零开始一步步用 PyTorch 实现一个推理 LLM。Implement a reasoning LLM in PyTorch from scratch, step by step

【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试资源平台。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、自动驾驶、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心跨周期知识。

Transformer 模型的高速推理引擎。Fast inference engine for Transformer models

RLHF 精选资源列表（持续更新）。A curated list of reinforcement learning with human feedback resources (continually updated)

终端中的 Agent，配备本地工具：编写代码、使用终端、浏览网页。在其之上构建你自己的持久化自主 Agent。Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

高质量且极速的预训练深度学习模型与 demo。Pre-trained Deep Learning models and demos (high quality and extremely fast)

TypeDB：为系统而生，而非为记录而生。TypeDB: Built for systems, not records

一个覆盖文本、图像、视频与音频任务的统一多模态评估工具包。One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

免费学习如何使用 LLMOps 最佳实践构建端到端生产级 LLM & RAG 系统：源码 + 12 个实操课程。🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

面向 AI Agent 的开发者控制平面Developer Control Plane for your AI Agents

大型多模态模型 LMM 的开源评估工具包，支持 220+ LMM 与 80+ 基准测试。Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

一个持久化的开发工作空间，能够自我改进并延续于单个会话之外。A persistent workspace for development work that self-improves and continues beyond one session.

开源 LLMOps 平台：集成 prompt playground、prompt 管理、LLM 评估和 LLM 可观测性。The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

为 LLM 优化推理代理Optimizing inference proxy for LLMs

CSGHub 是 OpenCSG 团队开发的全新开源 LLM 管理平台，提供开源与本地化/SaaS 解决方案，功能对标 Hugging Face。兼容 Hugging Face Python SDK，全面掌控 LLM、数据集和 agent 的全生命周期。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 full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

针对加速基础设施和微服务架构优化的生成式 AI 参考工作流。Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

在 Kubernetes 上借助现代加速器实现 SOTA 推理性能。Achieve state of the art inference performance with modern accelerators on Kubernetes

ChatGPT、Claude 等 LLM 的所有前端 GUI 客户端汇总。Every front-end GUI client for ChatGPT, Claude, and other LLMs

任意模型，任意硬件，零妥协。基于 @ziglang / @openxla / MLIR / @bazelbuild 构建。Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

用于加速视频生成的统一推理与后训练框架。A unified inference and post-training framework for accelerated video generation.

可扩展至上千个微调 LLM 的 Multi-LoRA 推理服务器Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

由 AI 驱动的虚拟高管团队 —— 单一连贯的高管 persona，由 8 个 Claude 专家 agent 支撑（FastAPI + Next.js）。AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

AI Agent 的开源 context layer。PipesHub 将公司知识（Slack、Drive、Jira、GitHub、Microsoft 365 及 40+ 连接器）转化为权限感知的 workspace，Agent 可对其进行搜索、grep、导航和引用。支持 MCP、SDK 与内置 agent，可自托管。The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.

JVM 的便携式 AI Agent 运行时。一个 @Agent 类可通过一套 SPI 在 Spring AI、LangChain4j、Anthropic 或另外 9 个后端上运行。支持 token 流式输出、工具调用、人工审批，并通过 WebSocket、SSE、gRPC 或 WebTransport/HTTP3 提供治理能力。兼容 MCP、A2A 与 AG-UI 协议。Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

基于 PaddlePaddle 的高性能 LLM 与 VLM 推理部署工具包。High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

作为记忆层的 Agent SkillsAgent Skills as a Memory Layer

面向 AI Agents 的统一虚拟文件系统。The World's First Unified Virtual Filesystem For AI Agents

⚡FlashRAG：面向高效 RAG 研究的 Python 工具包（WWW2025 Resource）⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

面向 LLM 实验和 AI Agent 的评估与追踪Evaluation and Tracking for LLM Experiments and AI Agents

面向 LLM 评估和 AI agent 测试的平台The platform for LLM evaluations and AI agent testing