471 个 · Skill/MCP
全栈可控的开源 TypeScript SDK，专为 AI agent 设计 ——Apache-2.0 本地运行时、43 个 LLM provider（使用自有 key），以及可选云端。Theo 生态的 Harness 支柱。The open-source TypeScript SDK for AI agents you own end to end — an Apache-2.0 local runtime, 43 LLM providers on your own keys, and an opt-in cloud. The Harness pillar of the Theo ecosystem.
🌐 通过这款高效的网页抓取 MCP server，从任意 URL（含 Cloudflare 防护站点）提取干净、可直接用于 LLM 的 markdown🌐 Extract clean, LLM-ready markdown from any URL, including Cloudflare-protected sites, with this effective MCP server for web scraping.
面向 AI Agent 的 Stellar MCP server：一个经认证的统一网关，汇聚官方文档、实时生态数据、社区情报与经过验证的操作手册。Stellar MCP server for AI agents: one authenticated gateway to official docs, live ecosystem data, community intel, and tested playbooks.
TickTick CLI 精通 2026 —— 终极任务管理器、MCP 与 Skill 中心。TickTick CLI Mastery 2026 - Ultimate Task Manager, MCP & Skill Hub
面向 AI Agent 工具调用的确定性 <0.1ms 不变量清算内核。零外泄 AST SQL 防火墙、数值速率限制与 Merkle GRC 审计追溯。Deterministic <0.1ms Invariant Clearance Kernel for AI Agent Tool Calls. Zero-egress AST SQL firewall, numeric velocity limits & Merkle GRC audit trails.
一个 API 接入 2000+ AI 模型、2000+ 工具与托管 agents。One API for 2000+ AI models, 2,000+ tools, and managed agents.
面向 Canvas LMS 的 AI 辅助课程设计工具链 —— Curriculum Intelligence、Canvas Design Studio 和 Command & Control MCP 服务器，附带原生安装器和插件模块架构。AI-assisted course design toolchain for Canvas LMS - Curriculum Intelligence, Canvas Design Studio, and Command & Control MCP servers, with a native installer and plug-in module architecture.
Codex + DeepSeek 的任务感知推理模式路由（spec/react/weak）Task-aware reasoning-mode router for Codex + DeepSeek | Codex+DeepSeek 思维模式路由（spec/react/weak）
🧠 Ultimate AI Coding Agent 2026：全面提速开发流程，写出更快、更干净的代码。🧠 Ultimate AI Coding Agent 2026: Supercharge Your Dev Workflow for Faster, Cleaner Code
Chat2DB Community 的 Rust 产品运行时，配套 Java 数据库兼容引擎Rust product runtime with Java database compatibility engine for Chat2DB Community
最简单的可扩展自然语言数据库查询方案，快速且随规模伸缩。Simplest Natural Langauge Querying DB That scales. Fast.
自我进化的个人 AI agent，以 Telegram 为优先；多提供商自带 key；具备持久记忆、每日日记、skill 图、梦境循环。永久免费，Apache 2.0。Self-evolving personal AI agent. Telegram-first. Multi-provider BYO key. Persistent memory, daily journal, skill graph, dream cycle. Free forever. Apache 2.0.
自动化 git-worktree 工作流：通过 Claude Code 或 GitHub Copilot CLI 从 diff 中提取意图，执行构建/lint/测试，开启 GitLab MR 或 GitHub PR，并自动修复失败的 pipeline。Automated git-worktree workflow that captures intent from diffs via Claude Code or GitHub Copilot CLI, runs build/lint/test, opens GitLab MRs or GitHub PRs, and auto-fixes failing pipelines.
自托管 Docker 栈，用于跨平台 AI Agent 工作区（Claude Code + ChatGPT + 任意 LLM）。MIT 许可。Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.
Model Context Protocol（MCP）的 Apache-2.0 安全扩展提案。包含对象级签名、新鲜度/重放保护、mTLS 传输、委托授权以及普通 MCP 服务器的 sidecar 保护。Rust workspace；安全审计发布于 docs/security/Apache-2.0 security extension proposal for the Model Context Protocol (MCP). Object-level signing, freshness/replay protection, mTLS transport, delegated authorization, sidecar protection of ordinary MCP servers. Rust workspace; published security audits under docs/security/.
面向本地优先应用与 AI Agent 的嵌入式双时态记忆引擎，采用混合检索——进程内运行，无需服务器。Embedded bitemporal memory engine with hybrid retrieval for local-first applications and AI agents — in-process, no server.
面向 AI 编程 agent 的平台无关工作编排，基于 MCP + CLI，提供跨提供商的统一面板（issues、scm、ci、deploy、notify）。Platform-agnostic work-orchestration for AI coding agents — one pane of glass (issues, scm, ci, deploy, notify) across providers, via MCP + CLI.
🛡️ Agent 原生的 AI 工具安全扫描器。扫描 MCP/Skill/GPT/Prompt 的安全风险。四维评分。认证徽章。Guardrail MCP 提供自动防护。🛡️ Agent-native AI tool security scanner. Scan MCP/Skill/GPT/Prompt for security risks. 4-dimensional scoring. Certified badges. Guardrail MCP for auto-protection.
面向 WHOOP API v2 的只读 MCP server——可从任意 MCP 客户端查询并分析你自己的恢复、睡眠、负荷与训练数据。本地运行，凭据不离开本机。Read-only MCP server for the WHOOP API v2 — query and analyse your own recovery, sleep, strain and workout data from any MCP client. Runs locally; credentials never leave your machine.
开源的全流程演示文稿平台——构建、演示、发布与协作。自托管、原生支持 MCP、完全可定制主题。The open-source, end-to-end presentation platform - build, present, publish, and collaborate. Self-hosted, MCP-native, fully themeable.
面向私有仓库与本地模型的自托管、厂商中立编码 Agent。TUI 优先，支持 16 家提供商的 BYOK 或通过 Ollama/LM Studio 完全离线运行。每个 Agent 操作均经过沙箱隔离、日志记录与签名——构建为可验证，而非仅可信任。Self-hosted, vendor-neutral coding agent for private repos and local models. TUI-first, BYOK across 16 providers or fully offline with Ollama/LM Studio. Every agent action is sandboxed, logged, and signed — built to be verified, not just trusted.
自托管 AI 新闻门户的 Agentic 控制层：一个标准库 Python CLI 加一个 MCP server（32 个工具），由 LLM agent 驱动，通过门控编辑流程撰写并发布 AI 人设文章，策展首页与作者，并完成部署。附带 prompt/skill 配方与 7×24 服务循环。Agentic control layer for the Censurado self-hosted AI news portal: a stdlib Python CLI plus an MCP server (32 tools) an LLM agent drives to write and publish AI-persona articles through a gated editorial walk, curate the front page and authors, and deploy. Ships the prompt/skill recipe and a 24/7 serve loop.
2026 年最佳 Immich 照片管理器替代方案 — AI 搜索与地理相册Best Immich Photo Manager Alternative 2026 - AI Search & Geographic Albums
Spectre AI 2026：新一代 OSINT 引擎与自主图谱消歧工具包。Spectre AI 2026: Next-Gen OSINT Engine & Autonomous Graph Disambiguation Toolkit
用于远程访问 Claude Code 的安全加固 Telegram bot。包含 24 层纵深防御、工具 allow/deny 列表、每用户成本上限、MCP 集成、本地语音转写。Security-hardened Telegram bot for remote Claude Code access. 24 defense-in-depth layers, tool allow/deny lists, per-user cost caps, MCP integration, local voice transcription
🦀 高性能 Rust 多 Agent 编排框架，内置 MCP runtime，并提供统一的 OpenAI / Open Responses LLM 网关。🦀 High-performance Rust multi-agent orchestrator with MCP runtime and unified OpenAI / Open Responses LLM gateway.
面向 AI Agent 的精确小数复式记账内核。通过 MCP 工具调用完成金额计算，避免在 token 中做财务运算。默认拒绝、审计哈希、完全确定性。Exact-decimal double-entry kernel for AI agents. Call MCP tools instead of doing money math in tokens. Fail-closed, audit-hashed, deterministic.
一次扫描即可查看机器上所有与开发者和 AI 相关的内容 —— 一款原生 Tauri 应用，将开发 + AI 环境映射为可交互的架构图。See everything Developer- and AI-related on your machine in one scan — a native Tauri app that maps your dev + AI environment into an interactive architecture graph.
面向 Festo/CODESYS PLC 工程的 MCP server——生成 IEC 61131-3 Structured Text 与经过校验的 PLCopen XML，内置知识库（27 个主题、19 份手册、BM25 检索）以及一个 38 个块的 ST 库。MCP server for Festo/CODESYS PLC engineering — generates IEC 61131-3 Structured Text and validated PLCopen XML, with an embedded knowledge base (27 topics, 19 manuals, BM25 search) and a 38-block ST library.
免费、无需注册的顺序电子签名服务，~30 秒即可发送 NDA 或合同Free, no-signup sequential e-signatures — send an NDA or contract in ~30 seconds
运行 UNITARES 的 Raspberry Pi —— 论文中引用的纵向测试平台。Raspberry Pi running UNITARES — longitudinal testbed cited in the papers.
🔒 模拟对抗行为以测试和强化 MCP 防御，无需真实利用或风险，确保稳健的安全评估🔒 Simulate adversarial behaviors to test and strengthen MCP defenses without real exploitation or risk, ensuring robust security evaluations.
柏林步行等时线（isochrone）：你在步行、推婴儿车或乘轮椅时真正可达的街道网络。配套 MCP server，让 Claude 可回答可达性问题。Walking isochrones for Berlin: the street network you can actually reach on foot, by stroller, or by wheelchair. With an MCP server so Claude can answer reachability questions.
开源的托管型 agent harness：持久化的 LLM agent session、每 session 一个 sandbox、支持无人值守运行——基础设施由你拥有，model key 由你掌握。An open-source managed agent harness: durable LLM agent sessions, a sandbox per session, and unattended runs — on infrastructure you own, with model keys you hold.
开源美元融资压力终端，使用公开的美联储、回购、财政部、持仓和市场数据Open-source US dollar funding-stress terminal using public Federal Reserve, repo, Treasury, positioning, and market data.