Custom agents

Connects any MCP-compatible AI assistant to Siemens TIA Portal via the Openness API

Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.

Agent_Console（智能体控制台）是一个本地运行的 Agent + RAG 工作台。它把文档入库、混合检索、查询改写、工具调用、运行回调和人工审核放在同一个控制台里，适合做企业知识库问答、课程资料检索、客服辅助和可追踪的智能体实验

Forge — AI Software Engineer. An autonomous software engineering agent. Claude-powered, GitHub-native, deployable on Vercel.

A monorepo for creating, managing, and publishing reusable Agent skills (Claude Code skills).

Starter Template for developing a Next.js (16) + Firebase + MUI Project. This repository contains the necessary code to kickstart a project that includes authentication, server-side rendering, MUI components, analytics, and even sending emails

Generate verification-focused operating prompts for AI agents.

Language agnostic linter that keeps your code and documentation in sync and valid

KDNA Core — open .kdna judgment-asset file format, schemas, JS Core, and runtime loading contract.

Keeps Claude Code and Codex CLI sober-minded: calm, constrained, and evidence-driven.

Research-focused fork of Hermes Agent for autonomous end-to-end LLM research loops.

Project Doxa is an advanced, autonomous agent-based simulation engine where AI agents act as citizens of evolving civilizations.

An open-source agent workflow engine & meta-harness: orchestrates Claude, Codex, and Pi to run multi-step work as a folder-as-agent pipeline. Its flagship coding workflow turns a rough idea into a merge-ready PR; ships content too, and runs the workflows you author.

KyberBot — Your AI agent, your rules. Powered by Claude Code.

Complexity-aware agentic coding pipeline for Claude Code

Practical Agent Skills for Codex, Claude Code, Cursor, and compatible coding agents, focused on reusable workflows, skill discovery, evaluation, writing, research, and automation.

Turn your AI assistant into a senior web developer. Production-ready guides for SEO, performance, and agent-readiness - for Claude Code, Cursor, Copilot, and Windsurf.

The system of record and control plane for AI coding agents. Keeps their memory correct, current, and safe to act on as the code moves, captures what code can't say on its own, and gates what agents are allowed to do. Retrieves by path, semantic search, and relationship (code-graph).

互動式 IT 故障排除 Runbook，整合 Claude AI。涵蓋 CCTV、NAS、AD、Exchange、Outlook 等企業常見場景。純靜態 HTML，GitHub Pages 一鍵部署。AI-powered IT troubleshooting runbook for Active Directory, Exchange, Outlook, NAS, CCTV and manufacturing environments. Designed for real-world IT operations and support teams.

Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.

Research Math Agents, Official code release for our paper RMA

Autonomous agent for Minecraft, combining LLMs and Baritone pathfinding

Rustant is a high-performance, privacy-first autonomous personal agent built entirely in Rust, designed to execute complex tasks through LLM-powered reasoning while maintaining strict safety guarantees.

Autonomous AI experiment loop CLI -- run research overnight with any coding agent

These are multi-ai-agents samples for Cloud Native

Official Implementation of "O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL"

UAVs path planning algorithm based on multi-agent deep reinforcement learning algorithm MASAC

Bring Claude's Skills pattern to any MCP-compatible agent

Offline agent skill bundling specification.website (128 topics) for Claude Code and other SKILL.md-compatible agents. Spec content CC BY 4.0 by Joost de Valk.

A plugin to turn your Claude agent into a WordPress expert

Your AI-Powered Test Agent for Comprehensive Test Cases Generation and Effective Test Automation leveraging RAG architecture & GenAI

Agentic Chunking involves organizing propositions from a text into meaningful “chunks” for efficient processing and retrieval within a RAG system.

Goal-QA-driven development toolkit for agentic AI

Make your repo ready for Codex, Claude Code, Cursor, and contributors.

A verifiable, time-aware knowledge ledger your LLM keeps for you. An evolution of the LLM Wiki pattern, built on Claude Code.

Auto-evolving LLM Agent Harness - Benchmark-driven evolution via Claude Code + self_evolution.md guide

A curated collection of Agent Skills — reusable units of intelligence that teach AI General Agents how to perform specific tasks autonomously.

The official implementation of our work SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration in AAAI 2025

Idiomatic agent sdk inspired by the claude code source leak.

Build ANY project faster with parallel AI workers that never conflict. Drop the .planckatron folder into your project and say "Planckatron" to activate. Supports frontend, backend, fullstack, automation, agentic workflows, libraries, and monorepos.

A phased engineering process for Claude Code. Discuss, specify, plan; then let it build.

面向 Cursor / Codex / Claude 等 Coding Agent 的通用工作区模板，提供多仓项目注册、知识库索引、规则治理与技能体系，帮助团队把 AI 协作流程沉淀为可复用工程实践。

Agent skill to migrate a Webflow site to React.

A curated list of the OpenClaw family — the open-source AI agent ecosystem. From the 150K-star original to IoT chips, Rust frameworks, and security tooling.

Shared workspace for AI agents and human developers. See, audit, and review every change AI makes to your codebase. Multi-language graph (Python/TypeScript), MCP-native, local-first.

Hamiltonian decomposition of Z_m^3 Cayley digraphs for all m > 2 — a complete solution to Knuth's "Claude's Cycles," found by LLM agents under a structured exploration prompt. Constructions, proofs, Lean formalization, and a verification suite.

SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

Self-hosted web control plane for Codex, Claude Code, and AI coding agents running on your own machines.

AI-assisted XAUUSD daily research workflow with Research Skill, Agent Harness, LangGraph, Tool Calling, and free public data sources.

PPT-Design-DNA is a Design-DNA-driven HTML presentation skill that turns reference images into reusable visual systems, saves them as Design Profiles, and applies those styles to high-quality presentation decks. Not a template filler, but an AI visual system designer for PPTs.

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot, OCR, UI inspection) and an agent (autonomous mission engine, macro recorder, intent-based discovery, event watchers). Built with opencode (DeepSeek V4). Ships as MCP server, web UI, and Tauri desktop app.

NullFlux — 本地部署的中文 CFD / 科学计算智能体（OpenFOAM · MFIX · LBM · ParaView · 视觉核验 · 论文复现），by LZF

Plug-and-play MCP that gives your coding agent UI superpowers. One-line install, zero config. Claude Code, Codex, Cursor, VS Code, and more.

Computer-use, but for the iPhone — AI agents (and your browser) see and drive a real phone over macOS iPhone Mirroring. Low-latency WebRTC video, near-native touch, HTTP API + MCP. Rust, self-hosted.

《智能体工程：从一句话到一个闭环》（Prompt · Context · Harness · Loop），本书将大语言模型驱动的智能体系统拆解为四种递进的工程范式，四种范式从 Token 到 System，从一次调用到完整的自主闭环，构成了智能体系统的完整工程视图。

The official Qwen Studio app only supports Windows and macOS. This project brings the same desktop experience to Linux.

万相台 AI 无界 one.alimama.com 数据查询 + 单元关停 CLI · 23个已核实子命令(报表/推广/账户) · cookie 直读无需登录

A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.

AI 驱动的电商全流程自动化系统。选品、上架、客服、运营分析、货源筛选，基于 DeepSeek V4 + Ollama 混合模型路由，自驱型 ReAct Agent 框架

纯本地 AI 编程桌面工具 · 由 DeepSeek 驱动 · 一个 API Key 即用

Open-source AI front-office factory for agencies serving local businesses: website, booking, intake, CRM, and agents in one workspace. Self-hostable.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on collected agent rollout trajectories.

The local-first Agentic Knowledge OS - CLI-first, self-improving, measured. Turn intentions into traceable, auditable, reusable workflows. Runs on your machine (Ollama, Neo4j, Qdrant).

Protected remote debugging bridge for an existing iOS WKWebView

Agent-native LLM, RAG and Agent knowledge system with traceable Markdown, MCP tools and MkDocs.

Free web search for AI agents — multi-engine parallel, smart re-ranking, zero API keys. | 免费 AI 联网搜索 — 多引擎并行、语义重排、零 API Key

TELL: Test-time Experiential Lifelong Learning – a single LLM agent that learns from experience at test time, achieving 43.9% on ARC-AGI-3 with no training.

An autonomous AI agent for recruitment workflow automation.

MCP server that lets AI agents drive, test, and inspect WPF desktop applications through UI Automation. Attach to any running WPF app, explore screens autonomously, explain UI state, and generate regression tests — all via natural language through the Model Context Protocol.

A sample for multi-agent orchestration in Java using Azure Cosmos DB with Spring AI

Taiwan's first multi-platform AI Agent built by a student club, integrating multiple messaging platforms to provide 24/7 intelligent support.

WordPress plugin development skills for AI coding agents — Claude Code, Gemini CLI, Cursor, Windsurf, Cline, Codex, Copilot, opencode, and more

Weekly retro for your coding agent. A Claude Code skill that mines your session transcripts for recurring failures and turns them into evidence-backed CLAUDE.md fixes. Local-only, zero dependencies, MIT.

AI Agent for WordPress — agentic AI loop with tool-calling via the Abilities API

Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding

The open-source AISI toolkit for sandboxing agentic evaluations

帮助产品经理澄清模糊产品想法，分析需求、设计 AI 能力，并生成精简 Markdown PRD 的 Codex Skill。

My LLM Agent Learning

The open-source trading harness for Claude Code / Codex agents.

Spec-driven development (SDD) CLI for AI coding agents (Claude Code, Cursor) - initialize, validate, and sync .specs/ across TypeScript & Node.js projects

macOS 菜单栏工具，聚合显示多个 AI 编程/Agent工具（Claude Code / Codex / Cursor / Qoder / 悟空/ Workbuddy 等）的 token 用量，全本地直读零配置

Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

🔌 An Android Studio plugin exposing native Gemini tools as an MCP server. Enable external AI assistants (Claude, Copilot) to call Android-specific tools directly.

Pinned, hardened config stack for OpenCode + OpenRouter + oh-my-openagent (OmO). One install, OpenRouter-only routing, 19 models, deployment guards, content-aware uncensored routes, circuit breakers, cost-aware fallbacks.

Mi-Memory: A Composable, Evolvable, and Multi-Source Memory System for Daily Assistant Agents

Open catalog of web skills for AI agents — search, add, and run reusable browser recipes with whatever browser your agent already has.

Windows 灵动岛风格桌面助手，集时间、天气、日历、股票、待办、终端、通知与 AI 助手于一体，基于 Tauri 2 + React 构建。

Multi-language CLI for Rafter — the security toolkit built for AI coding agents and the developers who use them.

AI Reputation Manager for Claude Code. Analyze online reviews, score brand sentiment, benchmark against competitors, generate review responses, create crisis playbooks, and produce PDF reputation reports — 14 skills, 5 parallel agents.

基于 **Claude Agent SDK** 的亚马逊卖家全链路 AI 助手。集成 **54 个专业技能**，通过自然语言对话即可完成选品调研、关键词挖掘、Listing 优化、FBA 费用计算、PPC 广告等全链路工作。 ## 架构 ``` 用户浏览器 ←WebSocket→ Express Server ←→ Claude Agent SDK ←→ 54 个 Amazon Skills

RedSearcher's framework for deep search agent trajectory synthesis, QA filtering, and model evaluation, supporting ReACT and DeepSeek-style agent loops.

Live AI call copilot for macOS — real-time suggested answers, blockers, action items. On-device transcription, local-first: your calls never leave your Mac.

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

Fund Analysis Multi-Agent System (FAMAS) - 基于多Agent协作的基金深度分析、筛选与持续监控决策支持系统

通用个人知识库 vault，配合 cognition-hub Obsidian 插件与 Claude Code Agent 工作流，构成完整的认知生产管线。

Hermes profile distribution turning claude-trading-skills into an always-on US-equity research, journaling, and risk-review assistant for human traders. No order placement.

Удобная установка, настройка и управление Zapret2 через claude code или codex.

一个 agent skill：把一个主题做成封面/目录/每章插画/精排俱全、可直接出片的 PDF 书。多 agent 调研→逐章写作→配图→Typst 排版→事实核查。工具无关(Claude Code / Codex)、风格可插拔

A Swift framework for Final Cut Pro FCPXML processing built with AI agents