Trending
Agent Skills & MCP
Agent skills, tool definitions and Model Context Protocol servers.
Trending
New
Most starred
927 repositories ·
topics: mcp, model-context-protocol, agent-skills, llm-tools, function-calling
-
651MCP server for SSH: let Claude Code, Codex and any MCP client run commands, transfer files and manage servers over SSH, with human approval, an encrypted vault and a live audit trail. Desktop app and CLI included.+5.0/wkmeasured★ 53227
-
652写中文技术文档的 Agent Skill,基于阮一峰《中文技术文档的写作规范》:短句、平实、没有 AI 腔+1.7/daymeasured★ 40527
-
653⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.+4.0/wkmeasured★ 17727
-
654A Model Context Protocol server for converting almost anything to Markdown+3.0/wkmeasured★ 3k27
-
655Connect your users to their apps−2.7/daymeasured★ 15.7k27
-
656MCP Aggregator, Orchestrator, Middleware, Gateway in one docker+2.4/daymeasured★ 2.8k27
-
657Agent skill for rigorous bug bounty report triage, validation, severity escalation, and submission-ready reporting.+1.6/daymeasured★ 15027
-
658The smartest brains on earth, in an MCP. Cited, searchable MCP servers built from founders' talks, essays and posts.+1.1/daymeasured★ 9527
-
659On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.+4.0/wkmeasured★ 65327
-
660Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.+4.0/wkmeasured★ 64027
-
661Pi Coding Agent 中文学习蓝皮书:从安装与第一个可验收任务开始,逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。+6.0/wkmeasured★ 34327
-
662Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data+6.0/wkmeasured★ 24327
-
663Flopwire connects AI agents through messaging and shared history across harnesses, models, machines, and teammates.+1.1/daymeasured★ 9827
-
664A data platform for investment research. Ingests financial data sources and computes point-in-time financial metrics for valuation and screening. Delivered as an MCP server.+5.0/wkmeasured★ 32927
-
665Agent Skill for 15–90 s motion graphics, promo and character videos: reference analysis, seven stage gates, Remotion and HyperFrames engines.+1.0/daymeasured★ 13527
-
666Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.+2.0/wkmeasured★ 10827
-
667Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.−3.0/wkmeasured★ 8.9k26
-
668文子的小红书工作流:从账号定位、选题标题、真人化改稿、图文规划到排期复盘的一套可安装 Agent Skills。+6.0/wkmeasured★ 18926
-
669The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (limited), full support from Delphi 12 Athens.+1.0/wkmeasured★ 21626
-
670Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation+2.0/wkmeasured★ 39326
-
671[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal+1.7/daymeasured★ 3.9k26
-
672OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web.+2.0/wkmeasured★ 11926
-
673The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.+4.0/wkmeasured★ 43726
-
674Preline UI is an open-source set of prebuilt UI components based on the utility-first Tailwind CSS framework.+1.0/daymeasured★ 6.5k26
-
675Unofficial read-only MCP server for Digikala: search products, find the cheapest real match, compare sellers, price history, reviews, deals and Fresh supermarket for AI agents. دیجیکالا، مقایسه قیمت، ارزانترین، شگفتانگیز+1.3/daylifetime avg★ 4226
-
676Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.+4.0/wkmeasured★ 35926
-
677WhatsApp MCP Server for AI Agents - TypeScript, Baileys and Cloud API+1.0/daymeasured★ 6526
-
678麦门四重奏 McQuartet · 一个 Skill 装四个玩法:修行录 / 团餐指挥官 / 隐藏菜单实验室 / 每日运势签。基于麦当劳中国官方 MCP,187 个测试全绿,离线演示可一键复现。+1.3/daymeasured★ 14426
-
679OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.+2.0/wkmeasured★ 18326
-
680mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.+4.0/wkmeasured★ 1.6k26
-
681Open source health data aggregator and self-hosted Terra alternative. One API for wearable data from Apple Health, Health Connect, Oura, WHOOP, Withings, Fitbit, Dexcom and more: REST, FHIR R4, Open mHealth, webhooks, CSV/Parquet and a read-only MCP server. One Go binary plus Postgres. AGPL-3.0.+1.0/daymeasured★ 6126
-
682一句话,做成有封面、有动画的 Live 图。Turn a sentence into a Live Photo with a designed cover and animation.+6.0/wkmeasured★ 54526
-
683Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.+1.0/daymeasured★ 21926
-
6845ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .flatmeasured★ 5.4k26
-
685STC 简明技术性中文:给 AI 用的中文写作规范。输出更自然、简短,术语更一致,任务回执更清楚。支持 CLI、独立 Skill 和网页聊天。Simplified Technical Chinese: rules, a dictionary, and tools for clear, concise AI output.+6.0/wkmeasured★ 12026
-
686Fast, local, read-only MCP Server for WeChat (4.x/3.x) & DingTalk (7.x V2/V3) chat history with FTS5 search+1.1/daymeasured★ 8026
-
687剧本分镜智能体(PenShot):电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析,生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致,支持 MCP/REST API/Function Calls/A2A 集成。(LLM-powered text-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency)+4.0/wkmeasured★ 23626
-
688This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.+6.0/wkmeasured★ 19426
-
689You type. It already knows. Local LLMs that read and think while you type.+6.0/wkmeasured★ 8026
-
690🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.+1.0/wkmeasured★ 1.9k26
-
691Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.+1.1/daylifetime avg★ 11226
-
692A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows+1.0/wkmeasured★ 2.3k26
-
693Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.+1.0/daymeasured★ 14926
-
694Guide pédagogique non officiel en français sur REA (Reverse Engineer Anything) : analyser des applications et des binaires avec un agent de code via MCP et CLI, Hopper ou Ghidra, preuves à l'appui. Inclut le cadre légal de la rétro-ingénierie. Projet amont : morluto/rea.+1.6/daylifetime avg★ 4326
-
695One local board for Claude Code, Codex, Cursor and 5 more coding agents. See which session needs you, share your fleet card, start free on $0 models. Source-available.+4.0/wkmeasured★ 21626
-
696Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One command installs them into the tool you already use.+2.0/wkmeasured★ 79725
-
697Instant REST and MCP APIs for PostgreSQL and MySQL, on existing or new databases. CRUD, custom SQL routes, auth and ACL without writing a backend. Low-code, ⚡ realtime, high-performance. Native MySQL support since v2.5flatmeasured★ 4.6k25
-
698Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.−9.7/daymeasured★ 4.3k25
-
699Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included+2.0/wkmeasured★ 66025
-
700The LLM Anti-Framework+1.0/wkmeasured★ 1.5k25