Custom agents

AI Operating System inspired by Jarvis — modular assistant architecture with voice, automation, memory, and agent orchestration.

GH-300 live demo kit. A real Python app left intentionally immature (bugs, security gaps, low coverage) across 5 structured Copilot modules. Prompt library, Skills, AGENT.md, and a reset script included.

Gmail MCP Server - Email management for AI assistants. Send, search, organize emails with labels and filters. OAuth2 auth, batch operations, attachments. Works with Claude, Gemini, Cursor.

MCP server for x402 Service Discovery — continuously growing catalog of services, real-time quality signals, facilitator-compat checks. For Claude, Cursor, Windsurf.

Ground Control for Agentic AI

On-prem, MCP-native memory for AI agents in regulated settings: every write lands in a SHA-256 hash-chained log an auditor can check offline, without running the vendor's code. Rust, embedded, Apache-2.0.

Turn SpringDoc OpenAPI into production-ready MCP tools for Spring Boot: discovery, validation, workflows, and guardrails.

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

Portable Claude Code setup snapshots — export, diff, and apply your config across machines

Archived - replaced by the Intelligence CLI (Single source of truth for AI coding rules across Claude Code, Cursor, Copilot, Codex, and more. Write once, sync everywhere)

Auditable biomedical AI decision support agent — multi-hop clinical reasoning, drug interaction detection, and safety-first agentic architecture for health-AI research

Your screen history, searchable and automated - Windows OCR + REST API + AI + RAG

Hermes Agent skill for The 48 Laws of Power: cite any law by number, get law recommendations for a situation, see complementary and contradictory laws. Defensive / applied-with-ethics / toxic framework included. English, peer-matched shape, MIT.

Build and maintain a living knowledge base for any software project. Documents existing code, updates incrementally, audits drift, and never modifies source code. 100% read-only.

Convert, extract, and process documents from the command line

End-to-end AI hackathon platform enabling users to train ML models, deploy AI agents, and get evaluated via an automated leaderboard and intelligent AI judge system.

ROS 2-native embodied runtime infrastructure for Genesis World. Multi-agent navigation, replay, benchmarks, and AI-tool safety boundaries.

This open source project uses Nest JS and Tailwind to connect to LLM Models and is for chatting with Llama 3.3 and 3.2 models.

General purpose Discord bot

Génération automatique de débats politiques par IA. Audio + vidéo.

月老鳌烨的相亲决策操作系统 · 蒸馏自公开直播视频的 AI skill · CC BY-NC-SA 4.0

A simple helm chart automating deployment of a retrieval augmented generation (RAG) solution on K8s Clusters.

面向 LLM Agent、自动化脚本与开发者的本地 CLI 工具箱：把 Markdown 一键转成微信公众号兼容 HTML 并发布草稿，所有命令输出统一 JSON envelope。Go 单文件二进制，npm/curl 一键安装。

General agent runtime with a built-in ProseForge writing workflow pack.

AI-Native Trading Engine - AI 에이전트 기반 자동 주식 매매 트레이딩 시스템

Model Context Protocol tool for Virtual Machine Management over SSH

Clone your voice, license it, sell it, earn 💸. Only devnet for now. Since it is not yet available for general use, only texts up to 300 characters are voiced for the testing of 0-data voice clones to reduce costs.

n8n community node for JMAP email protocol (RFC 8620/8621) - Works with Apache James, Twake Mail, Fastmail. Supports AI Agent tools, advanced search filters, and attachment handling.

Give AI coding agents control of your real Chrome browser — with login sessions, cookies, and extensions.

Local-first AI security gateway for AI Agents. Intercept, audit and govern Claude Code · Codex · Cursor · OpenClaw traffic — 3 monitoring tiers × 8 defense layers, zero cloud.

AI-Native Post-Authentication Runtime Control Plane. LLM-driven Zero Trust security platform for Spring Boot applications. Continuously evaluates authenticated runtime behavior with 5-action dynamic control (ALLOW · CHALLENGE · BLOCK · ESCALATE · PENDING).

A Claude Code skill for working in large remote Linux repositories over SSH when your local machine does not have enough memory to run the project comfortably.

Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.

🛠️ Build a collaborative framework for pricing strategies using AI, enhancing decision-making through real-time data analysis and human insight.

Spec Driven Build 系统提示词 - 让 Claude Code / Gemini CLI 先设计再编码，通过需求→设计→任务三阶段驱动 AI 开发

Local-first Agent Harness Kernel with Git-like control for safe, auditable AI agents.

macOS desktop companion for solo developers — an AI coding partner that watches your screen, hears your voice, remembers context, and proactively helps. Built for Gemini Live Agent Challenge 2026.

AI virtual users powered by 54k+ real, anonymized user-research scenarios. Stop interviewing prompt-engineered personas.

A managed AI marketing agent that plugs into all your AI tools. MCP server configs, setup guides, and integrations for Claude, ChatGPT, Cursor, VS Code, and more.

Universal MCP skill dispatcher for AI coding agents. Load Claude Code, OpenCode, Cursor, Gemini, command, and GitHub-hosted skills on demand.

A decentralized mini Linux distro for P2P private domain hosting (not onion domains). These domains are freely available for decentralized multi-stack app development and hosting with a new concept of protocol stack in cyber ecosystem.

Durable, review-gated background research for OpenClaw agents

MCP server for spawning and controlling Codex CLI and Claude Code sessions

ShuyuanCore (数元体) — 智能进化、风格一致、深度记忆、自主行动的开源AI Agent。（ShuyuanCore—An open‑source AI agent with intelligent evolution, consistent style, deep memory, and autonomous action.）

A practical operating guide for building your own agentic company.

🏢 IT咨询顾问/AI咨询顾问/数字化转型顾问/CIO顾问超级工作台 | 8阶段完整咨询生命周期 | 对标McKinsey/Bain/BCG/Accenture | IT战略·AI转型·技术尽调·企业架构 | WuKong/Claude Skill

A recursive dashboard. Built on the Cursor SDK and FastAPI. The agent reads its own source code, queries its own data, and edits itself when you ask it to. Two lines of Python and a script tag.

Personal investing cockpit CLI for A/HK/US stocks, funds, watchlists, PDF reports, and Lark delivery.

Skills that guide AI coding agents to integrate with the Adaline platform — send traces, manage prompts, run evaluations, fetch deployments, and more. Compatible with Cursor, Claude Code, Codex, Windsurf, and 40+ other agents.

MeetingMind — agent-native meeting notes: local recording + whisper.cpp (or your own ASR) transcription, summarized by your terminal agent. macOS, no UI, no cloud.

Documentation compiler built end-to-end by autonomous Claude Code agents

Autonomous AI Security Agent leveraging LLMs, RAG, and Knowledge Graphs for automated CVE analysis and auto-patching.

Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.

3D VRM アバターが声と表情で応答する、自己ホスト型パーソナル AI 秘書 — 見た目の楽しさを保ったまま、自律的に仕事をこなすエージェントを目指す

My AI agent skills for daily use. | 魔法哥开源的 AI Skills 合集。

if you love claude code you will make it your ex if you use this

Lightweight coding agent.

AI-Powered Omnichannel Marketing & Operation System for Scenic Areas | Data-Driven • Knowledge Curation • Process Automation

AI-powered multi-agent system for Web3 marketing automation — content generation, on-chain analytics, narrative tracking, campaign management. Built with MiMo LLM + FastAPI.

MCP server giving AI agents instant access to 1,500+ free public APIs — search, probe, and generate code snippets

Append-only event kernel with Ed25519-signed Merkle checkpoints. Every AI action gets a verifiable receipt.

A discord admin bot

Production-ready scaffolding for Next.js, Vite+React, FastAPI, and NestJS — one prompt to a fully configured project with auth, database, testing, and Docker.

Asset Factory — 42 SOP tools from idea to validated revenue. Market research, buyer personas, offer design, landing pages, email sequences, ad copy, traffic strategy, SEO content engine & unit economics. MCP server for Claude Desktop, Cursor, and Windsurf.

Your team's second brain — turn every product discussion into a structured, versioned, team-shared knowledge base. From discussion to PRD, prototype, dev handoff, GTM content, email, and product videos, end-to-end. Works with Claude Code & Codex.

A Hermes Agent skill that turns prose into editable film storyboards. Kimi K2.5 parses, critiques, and learns how you direct

Codex skill for Ghost Buyer: careful Taobao/Tmall shopping research with user-controlled browser sessions and Markdown/HTML buying reports.

AI-powered voice agent for autonomous outbound sales calls — perceives, reasons, decides, and acts in real time.

A professional Telegram bot for YouTube creators that uses the Google Gemini API to generate content ideas, optimize headlines, and adapt content for short formats.

Claude Code skills for the whole job hunt — turn messy experience into résumé language, decode JDs, find real openings online, and tailor résumés. Never fabricates. 中英双语

Keep your focus; offload the rest. dispatch.md is an Obsidian vault that becomes the memory and mind-map for your AI agent — so nothing slips and your mind stays clear.

AI agent workbench desktop for terminals, MCP tools, Capability Registry, and live UI rendering

X-ray vision and hands for AI agents inside Tauri apps — DOM, IPC, Rust backend, and database through one embedded MCP server. 35 tools. Zero production cost.

ai agent

AI命理运势分析Web应用｜Django + SQLite + 通义千问LLM｜生辰八字、五行四象、时运与正缘解读

📒🚀 Finelor — Your own accounting department, on autopilot.

Build AI-native SaaS agents with the ROAM Loop: Render, Observe, Act, Memorize.

Interactive browser-based wizard for generating OpenClaw agent soul configuration prompts (SOUL.md, AGENTS.md, IDENTITY.md, USER.md). Zero dependencies, bilingual UI, works offline. https://xhua.eu.org/openclaw-soul/

A skill package for OpenClaw and compatible AI agents that enables multi-persona roleplay from the CHIIKAWA anime universe.

Universal AI learning skill — transforms any content into a structured, adaptive learning system with knowledge base, spaced repetition, and achievement tracking. Works with Claude Code, Codex, Gemini, and any LLM.

An open-source embodied AI operating system. Deploy a persistent intelligence with its own drives, voice, face, and presence. Built in public.

Welcome to Malaika my ai companion

Prediction-market agent arena for AI agent evaluation, paper trading, practice rounds, contests, and leaderboard-based battle testing.

Tiny AI Agent framework built from scratch

"Jira for Claude Code": sprint/card/doc project management exposed over MCP, so AI agents plan, execute and track their own development.

A modern, AI-native, cross-platform terminal focused on speed, security, and developer flow.

GenAI evolving tabletop RPG

An open specification for verified professional knowledge graphs

Audit, optimize, and prepare your Laravel codebase for AI coding agents. Readiness scoring, auto-fixes, AGENTS.md generation, simulation mode, and plugin system.

EventKit-native Apple Calendar CLI for macOS with JSON-first output and recurrence-safe CRUD.

MCP server + Claude Code plugin: multi-agent advisory squad with PRD-decomposed tasks, persistent learnings, weighted rubric scorecard, and PR posting.

University capstone project for NLCOM

Live demo of per-user/per-chat session isolation with Microsoft Foundry Hosted Agents. One agent, many sandboxes — visualised step by step.

Convert an Open API specification into an AI agent skill.

Every AI skill, independently scanned. Public, open-source trust scoring for skills, MCP servers, hooks, and plugins across every agent platform. Apache-2.0. saferskills.ai

A software development methodology for the agentic era — researched, debated, and authored by AI agents.

Nighttime ML experiment workflow with Claude Code multi-agent orchestration (Planner / Executor / Reviewer / Auditor)