仓库/Skill 库

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 .

面向中小企业的 AI 运营层。将 Telegram、WhatsApp、Slack、Discord、GitLab、cron、webhook 以及 mesh 任务路由到基于 Claude、OpenAI 或任意 LLM 的 AI agent。非技术运营者使用 Web 向导，工程师使用 CLI。支持自托管。AI operations layer for small & medium businesses. Route Telegram, WhatsApp, Slack, Discord, GitLab, crons, webhooks, and mesh tasks to AI agents on Claude, OpenAI, or any LLM. Web wizard for non-technical operators, CLI for engineers. Self-hosted.

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

Jaz 的完整 agent 技术栈。包含插件、Skills、MCP 工具和 CLI，支持 Claude Code、Cowork、Codex、Copilot、Cursor 等。Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

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.

为 AI 编码 Agent 提供调用图上下文——展示调用者、测试与 blast radius，让 Agent 安全地变更代码。CLI 与 MCP。MIT 许可。Call-graph context for AI coding agents — surfaces callers, tests, and blast radius so agents make changes safely. CLI and MCP. MIT.

面向本地 AI Agent 的免费跨平台 UI，可在移动端、桌面端或无头 Docker 上编排 Ollama、嵌入式 GGUF 模型、DuckDB RAG 及 MCP 工具，无需 YAML 配置。A free, cross-platform UI for local AI agents. Orchestrate Ollama, embedded GGUF models, DuckDB RAG, and MCP tools on mobile, desktop, or headless Docker without YAML configs.

运行在你 PC 上的开源 AI 内容工厂——自动发现主题、调研、撰写、多模型 QA 审核并发布。基于 Ollama 本地优先，$0 API 成本。The open-source AI content factory that runs on your PC — discovers topics, researches, writes, reviews with multi-model QA, and publishes. Local-first via Ollama, $0 API costs.

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.

AI 驱动的初创公司情报 Agent——手写 ReAct 循环、并行工具执行、实时联网搜索以及 RAG 增强的文档分析。不依赖任何框架，具备完整理解能力。AI-powered startup intelligence agent — hand-built ReAct loop, parallel tool execution, live web search, and RAG-grounded document analysis. No frameworks. Full understanding.

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.

AI-Factory — 自主流水线，自动设计、构建、测试并发布产品。AI-Factory — autonomous pipeline that designs, builds, tests, and publishes products.

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.

基于大语言模型的智能研发效能助手。深度解析需求文档，精准识别逻辑漏洞；多维度生成测试用例，提升用例设计效率；构建可复用的测试知识库，将个人经验转化为团队资产。赋能 QA ，实现质量保障智能化。

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.

🤖 使用 SurfSense 增强你的研究——一个可定制的 AI Agent，可连接多平台，实现更智能、高效的信息检索。🤖 Enhance your research with SurfSense, a customizable AI agent that connects to multiple platforms for smarter, effective information retrieval.

一个面向主权个人 AI 的开源协议——加密身份、加密保险库、点对点消息传递，以及优先保护隐私和真实性而非广告与营销的信任网络。MIT 许可。An open-source protocol for sovereign personal AI - cryptographic identity, encrypted vaults, peer-to-peer messaging, and a trust network which prioritises privacy and truth over ads and marketing. MIT licensed.

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.

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.

🔍 使用 DeepSearch 自动化数字足迹分析，借助高级 Google 搜索操作符高效收集多平台洞察。🔍 Automate digital footprint analysis with DeepSearch, using advanced Google search operators to gather insights from multiple platforms efficiently.

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.

builderr.ai 交易 Agent 模板——fork 后实现 decide()，即可提交。Trading agent template for builderr.ai — fork this, implement decide(), submit.

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

2026 年顶级开源 AI Agent 🤖 | 最佳自主工具与框架Top Open-Source AI Agents 2026 🤖 | Best Autonomous Tools & Frameworks

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.

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.

多模型协作与智能辩论平台 — Multi-Agent 并行工作流 + RAG + 知识图谱，让多个 AI 像专家团队一样辩论、推理、共创

自治 AI 的形式化框架——Neural Parliament、Ulysses Contracts、Identity Layer。提供参考实现与 Lean 验证的证明，Apache-2.0 许可。Formal framework for self-governing AI — Neural Parliament, Ulysses Contracts, Identity Layer. Reference implementation, Lean-verified proofs, Apache-2.0.