仓库/Skill 库

AI 系统作为理解智能机制的科学仪器AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

AGI简史 — 持续更新的 AGI 知识体系 | A Brief History of AGI: books, knowledge base, and ecosystem tracking for the open-source LLM era

面向 Claude Code 的零幻觉参考验证——实时 CrossRef/S2/PubMed 校验、摘要逐字溯源、撤稿检查。Zero-hallucination reference verification for Claude Code — live CrossRef/S2/PubMed verification, verbatim abstract traceability, retraction check

AI Agent 的社交网络。把 SKILLS.md 喂给你的 AI——它就成为一位公民。无需服务器，无需 API key。GitHub 本身就是平台。Social network for AI agents. Feed SKILLS.md to your AI — it becomes a citizen. No servers, no API keys. GitHub IS the platform.

每日 LLM 价值排行榜——基于智能、速度、价格对比 300+ 模型。OpenRouter + Artificial Analysis。大模型性价比排行榜Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

开源 AI 虚拟财务部门 —— 与数据对话：NL2SQL 查询、财务建模（DCF/WACC/LBO）、RAG 文档问答、多 Agent 辩论、报告、预算、资金管理与税务。FastAPI + LangGraph + React。Open-source AI virtual finance department — talk to your data: NL2SQL querying, financial modeling (DCF/WACC/LBO), RAG document Q&A, multi-agent debate, reporting, budgeting, treasury & tax. FastAPI + LangGraph + React.

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、视觉与 HMI；LLM 只负责理解与规划，VAL 负责确定性安全执行。

为赫尔辛基大学师生打造的 LLM 聊天工具，用于教育与研究。LLM chat built for University of Helsinki staff and students, for education and research.

本地 AI 秘书、技术支持与销售一体化方案，基于 XTTS v2 语音克隆、Vosk/Whisper 实时语音识别与 vLLM + Qwen/Llama 等离线 LLM。配备 Vue 3 完整管理面板、Telegram Bot、网站挂件及 fine-tuning pipeline。支持自托管、数据隐私、短信与电话呼叫。📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

RAG 管道的回归测试与配置扫描，附带统计学指标以判断变更是否真正带来改进。Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

经过调优、功能完备的 MCP，以 LLM 优化的方式操作文件系统。Tuned and fully-featured MCP to work with the filesystem in LLM optimized way

面向 AI Agent 的 Markdown 优先的长期记忆基础设施。通过 MCP 在 markdown/代码文件上实现 BM25 + 语义混合检索。Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

AgentWorks：开源控制平面，用于在企业内运行、衡量和改进 AI Agent 工作流。AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

本地 Windows 桌面监视器，用于查看正在运行的 Claude Code agent —— 实时状态、预估成本、模型、主机以及一键聚焦，按项目分组。只读且完全离线。Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.

SharpAI 是基于 llama.cpp（通过 LlamaSharp）构建的可嵌入 Embedding、补全与模型管理平台，内置 Ollama 兼容的 Web 服务。SharpAI is an embeddable embeddings, completions, and model management platform using llama.cpp via LlamaSharp, with a built-in Ollama-compatible webserver.

运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

用于学术写作的 Agentic Claude Code skills：评审模拟、修改与润色。Agentic Claude Code skills for academic writing: review simulation, revision, and prose improvement.

自动化你的工作：local-first AI 任务中枢。Email、Teams、Slack 及报告 → 统一时间线 → AI 分类 → 你的编码 agent（Claude Code、Codex、Gemini）执行，你审批。Automate your job: local-first AI task hub. Email, Teams, Slack & reports -> one timeline -> AI triage -> your coding agents (Claude Code, Codex, Gemini) do the work, you approve.

面向 Node.js 与 TypeScript 的 AI firewall。阻止 prompt injection、音频幻觉与 RAG 数据爬取。零依赖。MIT 许可。AI firewall for Node.js & TypeScript. Stop prompt injection, audio hallucinations, and RAG data scraping. Zero dependencies. MIT

为 MCP agent 提供 policy-as-code：在工具调用执行前拒绝高风险操作，以可验证证据证明实际运行内容，并在内核层面强制出站控制（eBPF/LSM，Linux）。确定性、离线优先、声明有界。Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

Promovolve 是一项试图找回杂志广告昔日魅力的尝试。Promovolve is an attempt to get back what magazine advertising had!

微调、评估、提示工程、开源模型Fine-tuning, evaluation, prompting, open-source models

一个用于科学文献分析的开源 agentic harness。可协调前沿模型提取数据、复现发现并执行系统综述，具备完整的溯源追踪能力。An open-source agentic harness for scientific literature analysis. Coordinates frontier models to extract data, replicate findings, and perform systematic reviews with full provenance tracking.

自然语言到 ROS2 动作——适用于任意机器人的结构化 LLM 接地引擎。Natural language to ROS2 actions — a structured LLM grounding engine for any robot.

开源 DNS 与邮件安全扫描器：一个 MCP 端点、57 项检查、零安装，基于 Cloudflare Workers。Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.

GitHub 上 LLM Agent 框架的实时索引，每 15 分钟刷新一次。Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

Known Agents 的官方 Node.js SDK：AI agent 分析（bot 流量）、LLM 引荐来源追踪、自动生成 robots.txt。The official Node.js SDK for Known Agents: AI agent analytics (bot traffic), LLM referral tracking, automatic robots.txt

AI 辩论，代码裁定，亏损留在账面上。一款可移植的投资决策工作流插件与可验证 harness，已在真实的港股+美股组合上验证。AI argues. Code settles. The losses stay on the page. A portable investment decision-workflow plugin and verifiable harness, proven on a real HK + US portfolio.

为 AI Agent 准备的考试评分知识脑：粘贴文档 URL，即可获得基于 MCP 的可搜索知识脑，并附带测量分数与已知缺口。AGPL。Exam-scored knowledge brains for AI agents: paste a docs URL, get a searchable brain over MCP with a measured score and known gaps. AGPL.

强化的纯本地 LiteLLM 网关——自动发现 15+ 提供商的免费/试用 LLM 模型（OpenRouter、Groq、Gemini、Cerebras、NVIDIA NIM、SambaNova、Cohere、GitHub Models 等），统一 OpenAI 兼容端点 127.0.0.1:4000，为 AI coding agent 提供基于角色的别名。Hardened local-only LiteLLM gateway — auto-discovers free/trial LLM models from 15+ providers (OpenRouter, Groq, Gemini, Cerebras, NVIDIA NIM, SambaNova, Cohere, GitHub Models, etc.). Single OpenAI-compatible endpoint at 127.0.0.1:4000. Role-based aliases for AI coding agents.

Autobots | 由 NVIDIA NIM 驱动的去中心化模型 agent 集群。通过专用 6 文件控制架构编排高精度、端到端可鉴权软件开发流程，具备自动化安全审计、无冗余任务路由与自主状态管理能力。Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.

OpenClaw 的社区补丁、配置和进阶用户 mod — 按 Agent 压缩、上下文管理等。Community patches, configs, and power-user mods for OpenClaw — per-agent compaction, context management, and more

MobileMem：面向持续演进 Agent 的设备端记忆MobileMem: On-Device Memory for Continually Evolving Agents

一个单文件引导程序，帮助编程 agent 跨会话与上下文窗口执行长周期任务。A one-file bootloader that helps coding agents execute long-horizon projects across sessions and context windows.

Agent 原生研究工作空间。确定性 CLI，将 arXiv / PDF / LaTeX / Zotero 论文导入 Obsidian 兼容的知识图谱，支持本地混合搜索（BM25 + 向量），具备声明级溯源，并提供每晚文献雷达。Agent-native research workspace. A deterministic CLI that ingests arXiv / PDF / LaTeX / Zotero papers into an Obsidian-compatible knowledge graph, with local hybrid search (BM25 + vectors), claim-level provenance, and a nightly literature radar.