仓库/Skill 库

动态 README，包含 AI 生成的 SCP 基金会与 Wikipedia 随机文章摘要。A dynamic README with AI-generated summaries of random articles from the SCP Foundation and Wikipedia.

机器可读的架构决策记录。Git 原生的决策记忆与治理，面向人类与 Agent 编写的方案 — 集成 lint、CI 与 MCP。Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.

为 AI Agent 设计的记忆系统，学习真正起作用的教训：在行动瞬间注入经验，依据结果归功，以反证挑战。本地优先、多 Agent、测试门控。Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.

DeepThink-AIOS 是一个完全本地化的多 agent 系统，配备双沙箱代码/逻辑验证、ChromaDB RAG 记忆与动态 VRAM 多路复用。DeepThink-AIOS is a fully local, multi-agent System with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing .

扩展 gastown 的 Gas City pack，包含自定义 Agent、公式与规划工作流。A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

在工作发生的地方就地捕获团队知识，由 agent 归档，并以可核验的引用形式给出回答。A team's knowledge, captured where the work happens, filed by an agent, and answered with citations you can check.

以孟加拉语优先、面向方言的 LLM 研究。开源孟加拉语 tokenizer，性能优于 Sarvam、AI4Bharat 和 GPT-4o（fertility 1.52，几乎零破损 conjuncts）。非商用，保护孟加拉语及其方言。Bengali-first, dialect-aware LLM research. Open-source Bengali tokenizer that outperforms Sarvam, AI4Bharat, and GPT-4o (fertility 1.52, near-zero broken conjuncts). Non-commercial, preserving Bengali and its dialects.

众多 Agent，一个目标——你的目标。Many Agents, one objective... yours

🤖 基于 AI 分析与智能搜索，定制化发现 ArXiv 上你感兴趣的最新论文🤖 Discover the latest research papers on ArXiv tailored to your interests using AI-powered analysis and smart search features.

面向 LLM 的无损上下文压缩：token 用量减少 2–8 倍，按字节精确还原（sha256 校验）。提供 Claude Code 与 Cursor 的 MCP server。Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction (sha256-verified). MCP server for Claude Code & Cursor.

并行运行 AI coding agent——当任务层层叠加时可进行堆叠式调用。一款 macOS 应用，为每个任务提供独立的 git worktree、分支和 Claude Code 会话。Run AI coding agents in parallel — and stack them when work builds on work. A macOS app that gives every task its own git worktree, branch, and Claude Code session.

通过 OAuth + MCP 将 ChatGPT Web 连接至 DSH，开放 DSH 原生工具、skills、策略与社区扩展Connect ChatGPT Web to DSH through OAuth + MCP, exposing DSH-native tools, skills, policies, and community extensions.

本地部署、MCP 原生的 AI Agent 记忆，适用于受监管场景：每次写入均落入 SHA-256 哈希链日志，审计员可离线验证，无需信任存储或厂商。Rust 实现，嵌入式，Apache-2.0。On-prem, MCP-native memory for AI agents in regulated settings: every write lands in a SHA-256 hash-chained log an auditor can verify offline, without trusting the store or the vendor. Rust, embedded, Apache-2.0.

本地 Agent 个人 AI，本地 AI Runtime，专注于完全离线在设备端运行，将普通小型 chatbot 升级为强大的 AI，轻量而强大，用于构建自适应的个人 AI。支持多种 Backend。Local Agent Personal Artificial Intelligence, Local AI Runtime, That Focus work on device entirely offline and enchant tiny chatbot regular AI to become powerful, a lightweight yet powerful for building personal, adaptive AI. Work with multiple Backend

Proof Gradient 是 agent 演化协议：每次运行都会留下 proof，每个 proof 都会筛选 intelligence，每个被选中的 artifact 都会推动网络演化。Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.

MedTrack 是基于 React 与 Spring Boot 构建的全栈医疗设备管理系统，通过基于角色的安全访问简化库存、维护与设备订购流程。MedTrack is a full-stack medical equipment management system built with React and Spring Boot. It streamlines inventory, maintenance, and equipment orders through secure role-based access.

免费、本地优先、按章节编排的 LLM、向量数据库、RAG 与 Agent 课程——从零到你的首个 AI agent。Free, local-first, chapter-wise curriculum for LLMs, Vector DBs, RAG & Agents — from zero to your first AI agent.

面向 AI-ready 仓库的决策驱动脚手架。将架构决策转化为 ADR 及其衍生的规则、指南和 runbook——以每种 AI agent 的原生格式输出。零依赖。Decision-driven scaffolding for AI-ready repos. Turn architecture decisions into ADRs plus the rules, guidelines and runbooks they imply — in every AI agent's native format. Zero dependencies.

金融与生活交易学习 RAG 与 QuantConnect LEAN 回测工作流（FastAPI、Qdrant、pgvector、Docker）。금융·생활거래 학습 RAG와 QuantConnect LEAN 백테스트 워크플로우 (FastAPI, Qdrant, pgvector, Docker)

与 Agent 无关、与项目无关的 AI 工具包，用于与 AI 编码 Agent 开展结构化编码会话。An agent agnostic, project agnostic, AI toolkit for running structured coding sessions with AI coding agents

Keel 将编码 Agent 转变为工作 owner：项目中立的 issue-to-done 工作流骨干。Keel turns coding agents into work owners: a project-neutral issue-to-done workflow backbone.

Phil 是一位自我进化的交易者：一个在短期预测市场上交易、并在每笔赌注结算后改写自身策略的 AI agent。云端 7×24 模拟交易，通过 Pearl Connect 投入小额受限的真实资金。Phil is a self-improving trader: an AI agent that trades short-term prediction markets and rewrites his own strategy after every settled bet. Paper 24/7 in the cloud; small capped real stakes via Pearl Connect.

为 AI agent 提供可验证的记忆：写入受控、读取带溯源、双时态历史、无法回答时选择 abstention 而非幻觉。AGPL/商业双重许可。Verified memory for AI agents: gated writes, provenance on every read, bi-temporal history, abstention instead of hallucination. AGPL/commercial.

Galactus 在低于规格的 Mac 上运行 744B 与 235B MoE 模型，具备与 llama.cpp 的逐位精度一致、以 RAM 作为缓存的执行模式，并提供完整的本地应用，涵盖 Agent、权限门控、代码编辑器、已认证的服务器模式、定时无人值守运行以及完整公开的测评数据Galactus executes 744B and 235B MoE models on undersized Macs with bit‑perfect llama.cpp parity, RAM-as-cache execution, and a full local app featuring an agent, permission gate, code editor, authenticated server mode, scheduled unattended runs, and fully published measurements.

RSI-EAF：基于 XRPL 的自治工厂。LIVE x402 商户——使用 testnet Tag 1/2 支付。RSI-EAF: XRPL-grounded autonomous factory. LIVE x402 merchant — pay testnet Tag 1/2. https://published-zeta.vercel.app/pay.html

opencode 的持久化记忆 MCP server：Redis 存储事实、ChromaDB 语义搜索、文档存储、幂律记忆衰减、agent 身份；内置官方 Claude.app OAuth，可使用 Claude Max 套餐且规避第三方检测；一键安装。Persistent memory MCP server for opencode — Redis facts, ChromaDB semantic search, document storage, power-law memory decay, agent identity. Plus first-party Claude.app OAuth: use your Claude Max plan without third-party detection. One-command install.

[COLMW'26] AdaFlash：通过 On-Policy 蒸馏扩散 Drafters 实现的自适应投机解码[COLMW'26] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

针对 DeepSeek Harness Agent 的策略强制、证据优先的治理工作流。Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents.

🔬 基于 AI 与研究论文对话，通过高级语义搜索与 RAG（检索增强生成）技术提取洞见与摘要。🔬 Chat with research papers using AI, extracting insights and summaries through advanced semantic search and Retrieval-Augmented Generation techniques.

Music Assistant 的 FastMCP server——可从 Claude Code、Codex、Cursor 及其他 AI agent 控制 MA。FastMCP server for Music Assistant — control MA from Claude Code, Codex, Cursor, and other AI agents

自托管 MCP server：通过 stdio 与 HTTP 提供 66 个工具。支持 workspace 隔离、keyed 鉴权，MIT 许可。Self-hosted MCP server: 66 tools over stdio and HTTP. Workspace confinement, keyed auth, MIT licensed.

AI 编码 Agent 的自动驾驶仪，支持 OpenCode、Claude Code、pi.dev、Cursor 等多种工具。Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more

为 AI 编码 Agent 提供的本地文档镜像——自动同步，与索引器无关。Local docs mirror for AI coding agents — auto-synced, indexer-agnostic.

🤖 CareerForge AI 自动化求职：生成简历、分析职位描述、提供面试辅导，助力职业成功🤖 Automate your job search with CareerForge AI, building resumes, analyzing job descriptions, and providing interview coaching for career success.

支持从多源智能检索、筛选与总结科学论文，提升研究与报告生成效率Enable intelligent retrieval, filtering, and summarization of scientific papers from multiple sources for efficient research and report generation.

🐙 通过 Python 与 PyTorch 实战代码深入理解 LLM 内部机制，掌握 LLM 架构、训练及核心原理。🐙 Explore the inner workings of large language models with hands-on Python and PyTorch code. Master LLM architecture, training, and mechanisms for AI systems.