仓库/Skill 库

Bionic 是 ChatGPT 的本地化部署替代方案，在保持严格数据机密性的同时提供生成式 AI 的能力Bionic is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

🏕️ 为开发者和 Agent 提供可复现的开发环境🏕️ Reproducible development environment for humans and agents

厂商无关的训练、推理与 Agent 负载编排，覆盖 NVIDIA、AMD、TPU 和 Tenstorrent，部署在云端、Kubernetes 和裸金属环境上Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

通过统一接口对接 LLM 服务商Communicate with an LLM provider using a single interface

统一管理 MCP Server 的应用（MCP Manager）。A Unified MCP Server Management App (MCP Manager).

基于 Envoy Gateway 构建，提供生成式 AI 服务的统一接入管理Manages Unified Access to Generative AI Services built on Envoy Gateway

NVIDIA AI Blueprint for video search and summarization（VSS）是一个 GPU 加速参考架构，用于构建具备实时验证告警、视觉问答与自动报告能力的视频分析 Agent。VSS Blueprint 采用 NVIDIA Cosmos 等视觉语言模型（VLM）、NVIDIA Nemotron 等 LLM，并结合 RAG 与 NVIDIA NIM。NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

快速、灵活、可移植的结构化生成。Fast, Flexible and Portable Structured Generation

AI Agents 喜爱的 Memory 方案！Memory that AI Agents Love!

原生支持 Agent 的机票与酒店搜索与预订 —— 提供 MCP server、CLI 以及 Python/JS SDK。覆盖数百家航空公司及主要预订平台，并附带每趟航班的可靠性历史。免费取消的酒店房价：先以小额预付款锁定房间，后续可通过链接在酒店截止日期前支付余款。Agent-native flight & hotel search and booking — MCP server, CLI, and Python/JS SDKs. Hundreds of airlines plus the major booking sites, with per-flight reliability history. Free-cancellation hotel rates: hold the room with a small upfront charge, then pay the balance later by link, up to the hotel's own deadline.

潜入 Shell 的幽灵。Ante 是一个自包含的 Agent 框架，核心高度优化。体验类似 Claude Code 或 Codex，但无其依赖与模型限制。Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.

DATGEN：AI 驱动的多 Agent 研究助手，自动完成假设生成、数据分析与报告撰写。DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

超快速 serverless GPU 推理、沙箱和后台任务Ultrafast serverless GPU inference, sandboxes, and background jobs

可扩展的 LLM 数据预处理与清洗工具集Scalable data pre processing and curation toolkit for LLMs

WFGY 正迈向 WFGY 5.0 Polaris Protocol，面向 AI reasoning、RAG、agents 与真实工作流的重要开源版本，包含 Problem Map、Global Debug Card、WFGY 4.0 与 CFV Easter EggWFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

在 Postgres 中可扩展、快速且节省磁盘的向量搜索，pgvecto.rs 的继任者。Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

2026 年 AI Agent 研究论文精选合集，涵盖 agent 工程、记忆、评测、workflow 与自主系统。A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.

用 Rust 编写的高性能 AI 编码 Agent CLI，零 unsafe 代码High-performance AI coding agent CLI written in Rust with zero unsafe code

高性能 AI 模型推理引擎A high-performance inference engine for AI models

Pixel-LLM 代码库官方仓库：Sa2VA（T-PAMI-26）、SAMTok（CVPR-26）、VRT（Arxiv-25）、SaSaSa2VA（LSVOS 第一名方案）。Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

开源 LLM/VLM 负载均衡器与服务平台，用于规模化自托管 LLM（和 VLM）🏓🦙 作为 llm-d、Docker Model Runner 等项目的替代方案，组件更少、部署更简单，基于 ggml 生态构建。支持 CPU 和 GPU。Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

开源、端到端的 LLM 与 AI agent 应用评估、观测与改进平台。Tracing · Evals · Simulations · Datasets · Gateway · Guardrails。可自托管，Apache 2.0 许可。Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

后端 Agent 构建工具 —— 多模态数据库、编排与服务，一个文件搞定The backend agents build with - Multimodal database, orchestration, and serving in one file

[GenAI 应用开发框架] 🚀 快速轻松构建 GenAI 应用 💬 在代码中使用结构化数据和链式调用语法与 GenAI Agent 交互 🧩 使用事件驱动的 *TriggerFlow* 管理复杂的 GenAI 业务逻辑 🔀 无需重写代码即可切换任意模型[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

自学习 Agent 浏览器Self-learning agent browser

面向 LLM、VLM、DiT 和 REC 模型的高性能推理引擎，针对多种 AI 加速器进行了优化。该项目托管于 OpenAtom 基金会。A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

构建 Agent 的更高标准Standards for building agents, better

基于 nvidia-smi 二进制工具的 Nvidia GPU Prometheus exporterNvidia GPU exporter for prometheus using nvidia-smi binary

通过统一 API 接口路由、管理和分析跨多家服务商的 LLM 请求Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

用于加速工作流程的自定义 AI Agent 平台Custom AI agent platform to speed up your work.

兼容 OpenAI 和 Anthropic 协议的 Apple Silicon 服务端。可运行 LLM 和视觉语言模型（Llama、Qwen-VL、LLaVA），支持 continuous batching、MCP 工具调用与多模态。原生 MLX 后端，速度达 400+ tok/s，兼容 Claude Code。OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

AI 编程 Agent 的实用命令行工具。A Utility CLI for AI Coding Agents

高性能推理引擎，支持 LLM、VLM、DiT 和 REC 模型，针对多种 AI 加速器优化A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

Agor — 团队 Agentic 事务指挥中心Agor - team command center for all things agentic

面向人类与跨厂商 AI Agent 的开源协作空间。每个 Agent 拥有独立的名称、记忆、技能和工作站。任意运行时，使用你的基础设施——不按 Agent 收取费用。Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个