仓库/Skill 库

开源 AI 同事，具备记忆能力Open-source AI coworker, with memory

AI Agents 的记忆层。用无服务器、单文件的记忆层替代复杂的 RAG pipeline，为 agents 提供即时检索与长期记忆。Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

Memori 是面向 Agent 的记忆基础设施。它是一个与 LLM 无关的中间层，可将 Agent 执行与对话转化为结构化、持久化的状态，用于生产系统。Memori 面向企业级场景，能够与现有数据基础设施协同工作，无需替换，并支持在托管云、单租户云、VPC 以及本地部署等多种环境中落地。Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

结构化输出（Structured Outputs）Structured Outputs

一个轻量、极速的进程内向量数据库。A lightweight, lightning-fast, in-process vector database

面向机器学习的 Tensor 库Tensor library for machine learning

🎨 TypeScript 的穷尽式 Pattern Matching 库，具备智能类型推断。🎨 The exhaustive Pattern Matching library for TypeScript, with smart type inference.

由 LLM 驱动的自动化渗透测试 Agentic 框架Automated Penetration Testing Agentic Framework Powered by Large Language Models

Nano vLLM。Nano vLLM

Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animated short dramas. Features AI scriptwriting, storyboarding, character and video generation. A cross-platform desktop app for efficient content creation.

20+ 高性能 LLM，并附带大规模预训练、微调与部署的 recipes20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Unity MCP 在 AI 助手与 Unity Editor 之间充当桥梁，让 LLM 具备管理资源、控制场景、编辑脚本以及自动化任务的能力。Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

NVIDIA® TensorRT™ 是在 NVIDIA GPU 上进行高性能深度学习推理的 SDK。本仓库包含 TensorRT 的开源组件。NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

💡 面向语义搜索、LLM 编排与语言模型工作流的一体化 AI 框架💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

超快的 AI Gateway，集成 guardrails。通过一个快速友好的 API 路由到 1,600+ LLM 和 50+ AI Guardrails。A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

先记录，后整理。一款 local-first 的 Markdown 应用，借助 AI 将零散记录转化为清晰的笔记。Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.

Pocket Flow：代码库到教程Pocket Flow: Codebase to Tutorial

现代生成式 AI 项目与服务的精选清单A curated list of modern Generative Artificial Intelligence projects and services

在云端以 OpenAI 兼容 API 端点形式运行任意开源 LLM，例如 DeepSeek 和 Llama。Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

复旦大学开源的工具增强对话语言模型An open-source tool-augmented conversational language model from Fudan University

BISHENG 是面向下一代企业 AI 应用的开放 LLM devops 平台。强大且全面的功能包括：GenAI workflow、RAG、Agent、统一模型管理、评估、SFT、数据集管理、企业级系统管理、可观测性等。BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

TensorZero 是一个开源 LLMOps 平台，统一了 LLM gateway、可观测性、评估、优化与实验TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

LMCache：借助最快的 KV Cache 层为你的 LLM 加速。LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

一个 Claude skill，可为任何 AI 工具撰写精准 prompt。零 token 或额度浪费，完整保留上下文与记忆。A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

Pocket Flow：一个仅 100 行代码的 LLM 框架。让 Agent 构建 Agent！Pocket Flow: 100-line LLM framework. Let Agents build Agents!

AI 可观测性与评估。AI Observability & Evaluation

示例 📓 Jupyter notebooks，演示如何使用 🧠 Amazon SageMaker 构建、训练和部署机器学习模型。Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

HexStrike AI MCP Agents 是一个高级 MCP 服务器，让 AI agent（Claude、GPT、Copilot 等）能够自主运行 150+ 网络安全工具，用于自动化渗透测试、漏洞发现、漏洞赏金自动化和安全研究，无缝桥接 LLM 与真实世界的攻击性安全能力。HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Triton Inference Server 提供针对云端和边缘推理优化的解决方案。The Triton Inference Server provides an optimized cloud and edge inferencing solution.

SkillOpt 是一个文本空间优化器，通过轨迹驱动的编辑、验证门控的更新，以及可部署的 best_skill.md artifact，为冻结的 LLM 智能体训练可复用的自然语言技能。SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

120+ LLM 库的分类精选清单A curated list of 120+ LLM libraries category wise.

OpenVINO™ 是用于优化和部署 AI 推理的开源工具包OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

基于 PyTorch 的 YOLOv3、YOLOv3-SPP 和 YOLOv3-tiny 实时目标检测实现，支持训练、验证、推理与多格式导出。PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

开源免费——历经阿里巴巴规模实战检验。混合架构代码审查工具：确定性流水线 + LLM Agent，精确的逐行注释，内置微调规则集（NPE、线程安全、XSS、SQL 注入），兼容 OpenAI 与 Anthropic。Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

全栈 MCP 框架，用于开发面向 ChatGPT / Claude 的 MCP Apps 以及面向 AI Agent 的 MCP Servers。The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.