仓库/Skill 库

AI 代码审查，完全掌控模型选择与成本。AI Code Review with Full Control Over Model Choice and Costs.

RTP-LLM：阿里巴巴面向多样化应用的高性能 LLM 推理引擎。RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

基于 Rust 🦀 构建的高性能、模块化、内存安全、生产可用的推理、数据接入与索引系统Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

社区最全面、持续更新的 LLM 软件漏洞检测研究索引——涵盖函数级、仓库级、Agent 级以及智能合约检测方向的论文，并附数据集、基准和综述The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.

一个使用模拟的、真实的合成交互对 Agent 进行全面诊断和优化的框架。A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

让 LLM KV cache 压缩变得更简单LLM KV cache compression made easy

开源 AI Agent 治理与编排框架：以声明式方式编写规则，Bernstein 强制执行并生成可验证、可回放的记录。免费，Apache-2.0。https://bernstein.runThe open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

基于 OpenSearch 构建的开源、自托管企业及站内搜索服务器，爬取网页、文件、数据库与云端数据源，支持 20+ 语言、REST API，以及 AI/RAG 与语义搜索。Apache-2.0。Open-source, self-hosted enterprise & site search server built on OpenSearch. Crawls web / file / DB / cloud sources, 20+ languages, REST API, and AI/RAG & semantic search. Apache-2.0.

轻量、可移植的 LLM 沙箱运行时（代码解释器）Python 库。Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

统一的 TUI 和 CLI，用于跨 11+ 个提供商索引和搜索你的本地 coding Agent 会话历史（Codex、Claude、Gemini、Cursor、Aider 等）。Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, Claude, Gemini, Cursor, Aider, etc.)

[EMNLP 2024 Demo] MarkLLM：面向 LLM 水印的开源工具包[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。

面向 LLM 和 LVLM 的强大模型压缩框架，适配 NVIDIA GPU 和华为昇腾 NPUA powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.

Rust 库，用于本地生成向量 embedding 和重排序！Rust library for generating vector embeddings and reranking locally!

开源、本地优先的写作工作空间，可使用 Claude Code 和 Codex 进行写作，并参考你自己的资料与过往工作。An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.

通过统一的基于 SQL 的框架，为人类和 AI Agent 提供 Cloud、SaaS、API 和 Model Context Protocol (MCP) 资源的查询、配给与运维能力。Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.

基于自主编码 Agent 的开源自动研究系统。运行 Claude Code、OpenCode 与 Codex，具备评分、共享知识与多 Agent 进化功能。被 COLM 2026 接收。Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

基于 Next.js、LangChain、PostgreSQL + pgvector 构建的 AI 驱动的初创企业加速引擎。可上传、组织并与文档对话。包含预测性缺失文档检测、基于角色的工作流以及页面级洞察提取。AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.

高性能且兼容 CommonMark 的 HTML 转 Markdown 转换器。由 Kreuzberg 团队维护。Kreuzberg 是一个以 Rust 为核心的快速多语言文档智能引擎，基于流式解析器与内置 OCR，支持从 98+ 文档格式中抽取结构化数据。High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 98+ document formats using streaming parsers and built-in OCR.

从零开始构建 LLM 驱动的多 Agent 应用Building LLM-Enabled Multi Agent Applications from Scratch

♾️ 基于 Spec Coding 的私有 Agent 集群。每个 Agent 拥有独立 GPU 加速桌面，可在完整私有 AI Stack 上运行 Claude、Codex、Gemini 及开源模型 ♾️♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

使用开源 LLM 摄取文件用于检索增强生成（RAG），无需第三方，数据不出你的网络。Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

面向任意文件格式的版本控制系统Version control system for any file format

TypeScript AI agent 框架：具备认知记忆、运行时工具锻造、多 agent 编排能力，支持 11 家 LLM provider。TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

将 Pi 打造成 el Gentleman：一套高级架构师级开发 harness，集成 SDD/OpenSpec、子 Agent、严格 TDD 证据、review guardrail 与 skill 发现机制。Turn Pi into el Gentleman: a senior-architect development harness with SDD/OpenSpec, subagents, strict TDD evidence, review guardrails, and skill discovery.

Second Brain 是一个 Agentic 框架，作为操作系统运行，利用本地文件智能、工作流自动化和 LLM 来完成任务，并通过多种模态和消息平台进行通信。Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

终端中的 AI 结对编程——单一静态二进制，亚毫秒级启动，支持任意模型。AI pair programming in your terminal — one static binary, sub-ms startup, any model

TypeSafe Jev 的有证据支撑的用例、模式、prompt 与入门代码——一个用于软件中快速、类型化、置信度感知决策的 System One 模型。Evidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast, typed, confidence-aware decisions in software.

极简网络搜索平台，配有可在浏览器直接运行的 AI 助手。Demo：https://felladrin-minisearch.hf.spaceMinimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space

本地 LLM 及图像/视频/音乐生成器；在手机上用本地模型实现类 Cursor 的 vibecode 编程体验。Local LLM, image&video&music generator, vibecode like cursor with local models on your phone

论文"LAMBDA: A large Model Based Data Agent"的官方仓库。https://www.polyu.edu.hk/ama/cmfai/lambda.htmlThis is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

一个面向动态文本分类的灵活、自适应分类系统A flexible, adaptive classification system for dynamic text classification

Athena 是一个本地优先的 agentic PKM，借助你自己的上下文帮助你做出更优决策——持久记忆、结构化推理，以及跨任意 LLM 工作的受治理 AI agent。拥有状态，租用智能。Athena is a local-first agentic PKM that helps you make better decisions with your own context — persistent memory, structured reasoning, and governed AI agents that work across any LLM. Own the state. Rent the intelligence.

关于大语言模型 On-Policy Distillation 的精选论文与资源合集A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

MIT 许可、无 COM 依赖的 .NET 库，用于创建、读取、编辑、转换、渲染和提取 Office、PDF、邮件、OneNote 及文本格式。MIT-licensed, COM-free .NET libraries for creating, reading, editing, converting, rendering, and extracting Office, PDF, email, OneNote, and text formats.

Pax 是一个基于 Jax 的机器学习框架，用于训练大规模模型。Pax 支持先进且完全可配置的实验与并行化，并已展现出业界领先的模型 FLOP 利用率。Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.