仓库/Skill 库

LitLLM：面向科学文献综述的工具包。LitLLM: A Toolkit for Scientific Literature Review

🪢 Langfuse API 的自动生成 Java 客户端。🪢 Auto-generated Java Client for Langfuse API

Promptfoo 的 GitHub Action。可用于测试 prompt、Agent 与 RAG；支持 LLM 的 AI 红队对抗、渗透测试与漏洞扫描；对比 GPT、Claude、Gemini、Llama 等模型的性能；通过简洁的声明式配置集成命令行与 CI/CD。The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

ELM 是将 LLM 应用于能源研究的一系列工具集合。ELM is a collection of utilities to apply Large Language Models (LLMs) to energy research.

一个 LLM 相关论文、学位论文、工具、数据集、课程与基准的合集。A collection of LLM related papers, thesis, tools, datasets, courses, benchmarks

⚡ Translate Markdown without breaking format — code blocks, LaTeX, links all preserved ｜ 翻译 Markdown 不破坏格式，代码块、LaTeX 公式、链接全保留

RuvNet Brain——基于 Reuven Cohen（rUv）的 RuvNet 技术栈（RuVector/RVF、Ruflo、AgentDB、RuLake、SPARC 及 21 个构建块）为 Claude Code 提供一个可下载、源码溯源的"大脑"。通过单一 MCP 工具（search_ruvnet）让 Claude 立足真实源码，而不是脱离技术栈空想。RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.

真实 AI Agent 安全事件、入侵和漏洞的精选时间线（2024-2026）。每条记录均标注来源和日期。A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

一个专为辅助研究活动而精选的 AI 工具列表，涵盖文献综述、引文管理、数据分析等工具，面向希望借助 AI 提升研究工作流的研究人员、学生和从业者。A curated list of AI tools specifically designed to assist in research activities, including tools for literature reviews, citation management, data analysis, and more. This repository is intended for researchers, students, and professionals who want to leverage AI to enhance their research workflows.

论文 LitLLMs, LLMs for Literature Review: Are we there yet?（TMLR 2025）的代码仓库。Code for LitLLMs, LLMs for Literature Review: Are we there yet? (TMLR 2025)

repo-map 生成由 LLM 增强的软件仓库摘要与分析，为开发者提供关于项目结构、文件用途以及跨编程语言潜在考量的洞察。repo-map generates LLM-enhanced summaries and analysis of software repositories, providing developers with valuable insights into project structures, file purposes, and potential considerations across various programming languages.

那条 API 背后究竟是谁？在浏览器中对任何 OpenAI 兼容端点进行指纹识别：9 项基础设施探针、并列对比、社区可扩展。Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison, community-extensible.

为 DeepSeek Harness 提供有界、分层、需审批、可审计的跨会话记忆（能力接缝：ctx.memory + SQLite provider + memory tool + 冻结快照注入）。Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

📚🔭 你的个人研究雷达 — 由 LLM 驱动的工具，可跨 arXiv / Crossref / Semantic Scholar / GitHub / RSS 自动聚合你关键词的最新论文。📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywords across arXiv / Crossref / Semantic Scholar / GitHub / RSS.

即插即用、成本高效且轻量化的长周期 LLM Agent 记忆插件A Plug-and-Play, Cost-Efficient, and Lightweight Memory Plugin for Long-Horizon LLM Agents

面向编程 Agent 的更快运行时。平均提速 25%、降本 30%，同时质量持平或更优。同等任务、同等质量，更快更便宜。Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.

Apeireth——一款基于 Rust 的 AGI 操作系统 / LLM 基座。85 个 crate：陪伴器官、世界模型、好奇心、假设检验、双层洋葱式安全Apeireth — An AGI Operating System / LLM Base (Rust). 85 crates: companion organ, world model, curiosity, hypothesis testing, double-onion security.

为你的 AI 助手提供真实的网络搜索、整页阅读与多源研究能力，引用内容绝不伪造。Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.

一款 WordPress 插件，使用 OpenAI API（GPT-4.5、o3）生成 SEO 优化、拟人化的长篇内容和图片。A WordPress plugin that uses the OpenAI API (GPT-4.5, o3) to generate SEO-optimized, humanized, long-form content and images.

双模式 AI 研究工作空间：DeepSearch 在约 2 分钟内将查询转化为带引用的网络报告；Research Mode 运行 25 个 Agent 的流水线，撰写完整学术论文（含 PRISMA 流程图、经核验的引用，导出 PDF/DOCX）；设有 4 个人机协同检查点；基于 LangGraph、FastAPI 与任意 OpenAI 兼容 LLM 构建AI research workspace with two modes — DeepSearch turns a query into a cited web report in ~2 min; Research Mode runs a 25-agent pipeline that writes a full academic paper (PRISMA diagram, verified citations, PDF/DOCX export). 4 human-in-the-loop checkpoints. Built with LangGraph, FastAPI, and any OpenAI-compatible LLM.

AI agents 的持久化加密记忆：一个 Rust 二进制，一个文件，无需云端。122 个标准 MCP 工具，混合召回，双时态历史，AES-256-GCM 加密。本地优先，支持气隙隔离，MIT 协议。Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 122 canonical MCP tools, hybrid recall, bi-temporal history, AES-256-GCM. Local-first, air-gap ready, MIT.

AI 编写软件的记录系统。实体、关系、变更与来源的持久化图谱，使人类和 AI Agent 在合并前看到变更影响范围。目前与 Git 并行使用。The system of record for AI-written software. A persistent graph of entities, relationships, changes, and provenance, so humans and AI agents see what a change touches before it merges. Beside Git today.

面向长时对话记忆层的综合基准测试框架A Comprehensive Benchmarking Framework for Long-Term Conversational Memory Layers

生产级多 Agent 编排引擎。从可插拔的 Agent、LLM、工具与 retriever 目录组合 Agentic 工作流；本地使用 LangGraph 执行，或通过 Temporal 分布式执行。内置 RAG 管道用于企业知识检索，支持 A2A 与 MCP 协议，提供可视化拖拽蓝图构建器。Production-grade multi-agent orchestration engine. Compose agentic workflows from a pluggable catalog of Agents, LLMs, tools, and retrievers. Execute locally with LangGraph or distributed with Temporal. Built-in RAG pipeline for enterprise knowledge retrieval. A2A and MCP protocol support. Visual drag-and-drop blueprint builder.

通过自然语言接口提供空间转录组学分析的 MCP server。MCP server for spatial transcriptomics analysis through natural language interfaces.

开源 AI Workforce OS：将 AI Agent 转化为执行业务职能、以结果衡量的自主劳动力。Claude Tag 的开源替代方案。The Open-Source AI Workforce OS. Turn AI agents into autonomous labor that performs business functions and is measured by outcomes. Claude Tag open source alternative

开源 FDE Agent 与企业 AI 约束层：24 条规则的 git-diff 审计、自动快照回滚、规则注入、自我进化。以 9 个 DeepSeek Harness 插件 + MCP server（66 个工具）形式交付。MIT 许可。Open-source FDE Agent & constraint layer for enterprise AI: 24-rule git-diff audit, auto snapshot rollback, rule injection, self-evolution. Ships as 9 DeepSeek Harness plugins + MCP server (66 tools). MIT.

一种基于大语言模型、采用人在回路的科学模式挖掘工作流A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

面向 AI Agent 的 Metasploit：扫描、攻击并修复 AI Agent 与 MCP 服务器。开源安全工具包Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

论文输入，灵感输出。从 2.5 亿+ 学术论文中生成研究、产品或功能创意。Papers in, ideas out. Generate research, product, or feature ideas from 250M+ academic papers.

📚 AI 驱动的论文阅读工作台。基于项目的论文问答，集成 Hybrid RAG、多 Agent 工作流（ReAct/Plan-Act/RePlan）、长期记忆与可溯源证据。使用 LangChain + LangGraph + Streamlit 构建。📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceable evidence. Built with LangChain + LangGraph + Streamlit.

ImageTrans 插件集合。Plugins for ImageTrans

面向终端的通用 AI 助手，让 Agent 之间共享可检索、可追溯且允许分歧的知识。让下一次判断，带着来源出发。

热门 claude-skills 与 AI Agent 仓库的自动更新排行榜，每 15 分钟刷新一次。Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes

开源、可自托管的 Claude Code 风格 agent 交付平台：现已支持 Slack，更多 channel 即将上线；同一 bundle 可在本地和 Kubernetes 上运行，git push 即可发布。Open-source, self-hostable delivery platform for Claude Code style agents. Connect Slack today, with more channels next. Run the same bundle locally and on Kubernetes, and ship it with git push.

AI 原生的结构化数据 wire 格式。在每个前沿模型上实现 100% 理解，比 JSON 减少 50-92% token，跨 17 种格式完成 43B+ 无损往返。Spec v3.4 Stable。The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.4 Stable.