GitHub 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产品经理超级工作台 | 12阶段·60+框架·20+交付物 | LLM·RAG·Agent·Prompt工程·AI评测·AI安全 | EU AI Act·深度合成新规·Token经济学 | WuKong/Claude/OpenClaw Skill

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

Local AI code review agent. Self hosted with Ollama, no data leaves your machine.

WWA Transform — Turn any website into an AI-powered agentfront. Claude Code plugin + Codex agent + CLI.

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.

AI agent skills for onboarding merchants to UCP (Universal Commerce Protocol). Audit → Profile → Catalog → Checkout → Validate.

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.）

Agent Studio with Federated Single Sign-On and Fine-Grained Access Controls

Tenki — autonomous AI quant agent. Natural-language backtesting with tamper-evident on-chain proof: every run card stored on Walrus and anchored on Sui, Mantle & Somnia.

A practical operating guide for building your own agentic company.

一款企业级多语言(Polyglot)智能出行 Agent 架构实战。采用 Monorepo 单仓管理，底层基于 Java Spring Cloud 构建高并发票务微服务底座；AI 大脑层提供 Java (Spring AI) 与 Python (FastAPI+LangChain) 双引擎实现。核心特性包含：端到端 JWT 上下文鉴权透传、基于 Tool Calling 的异常自纠错 (Self-Correction) 循环，以及微服务级的数据流压缩，完整打通自然语言到真实复杂业务下单的全链路闭环。

🏢 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.

AI copilot for TouchDesigner — DeepSeek v4. Standalone .tox (95 tools) + Claude Code MCP (110 tools, incl. td_ingest_url web ingestion). Activity log, OCR sidecar, tool approval gates, trace viewer, visual chat, BM25/FTS5 corpora, persistent memory, recipes, multi-model routing, compaction. TD 2025.32820+.

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.

Personal finance engine built for AI agents. Verified IRS reference data + deterministic financial calculations — tax, retirement, estate planning, Monte Carlo simulations. Fully offline, ~1ms.

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

Persistent knowledge memory for AI agents — tiny, dense pills of information stored in SQLite, served over HTTP, consumed via MCP.

Claude Code production runtime - Python implementation and prose chapters

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 customer support agent built with Python smolagents and InterSystems IRIS — SQL, RAG, and live interoperability

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

Convert PRDs into living Kanban boards. Claude Code skill.

Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.

An autonomous, 100% offline OS-level AI agent running on just 4GB VRAM. Built with Python, Ollama, and native tool-calling without MCP cache invalidation.

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.

Selective Disclosure for JWTs (SD-JWT) .Net implement

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.

VS Code & Cursor extension to manage AI coding agent sessions across git repositories and worktrees. Fork sessions, track changes, run quick actions. Supports Claude Code — extensible for other agents.

Autonomous Android AI Agent — Controls your phone screen like a human using AI vision + MCP remote control

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.

一站式游戏数据采集与自动化分析工作流，内置可视化 WebUI 与 AI Agent 助手。

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.

A universal, highly intelligent LLM API proxy gateway. Seamlessly translates heterogeneous AI protocols (OpenAI, Anthropic, Gemini) with built-in multi-account rotation, circuit breaking, and zero-config deployment.

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.

VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders

Real-time messaging between Claude sessions (CLI + Desktop + other-devices) — automatic ask/reply, no copy-pasting. Zero deps, localhost-first, MCP-based. Optional cross-network linking.

4torm - An open-source multi-agent collaboration platform. Chat, workflow, forum, and automation — all in one desktop app.

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

Agent skill for Spark Bitcoin L2 wallet capabilities including L402 for AI agents

Skill discovery engine for AI coding agents. One install, 20+ developer workflow skills.

ai agent

MCP Server for GitHub/GitLab code review - enables AI assistants to review pull requests and merge requests

Community template: Wire Sendblue iMessage to any AI agent (Hermes, OpenAI, Ollama) via n8n — with fallback, Redis retries, and Telegram alerts. Deploy on a single VPS in 15 min.

Personal RAG knowledge base assistant with FastAPI, Streamlit, LangChain, Chroma, Tavily, citations, evals, and request-id debugging.

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/

AI-SDLC framework of skills, rules, and agent definitions that AI coding agents use to generate consistent, production-quality Python code. Compatible with Claude Code, Codex, Cursor, Kiro, Windsurf, Gemini CLI, Antigravity, and GitHub Copilot.

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.

Agent Skill for bootstrapping, verifying, and enforcing agent-harness infrastructure in repositories | Claude Code compatible

Welcome to Malaika my ai companion

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.

Multi-agent orchestration tool for AI-assisted development with parallel agents and cross-review modes

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

统一的 AI 编程助手 Web 平台（Claude Code、Pi Agent、Codex）。实时流式输出、分屏并行、Agent 切换 Unified web platform for AI coding assistants (Claude Code, Pi Agent, Codex). Real-time streaming, split-screen parallel mode, agent switching, dark theme

💡 1,000 structured pain points for vertical AI. Every entry has persona, TAM, WTP, incumbents & the gap — plus 50 AI-cofounder validated. Zero-build static browser.

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.

Multi-agent system architecture design & harness guide based on Anthropic's official patterns — agent orchestration, optimization, and extensibility skill for Claude Code

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

Self-hostable execution engine for reliable, observable, tool-using AI agents — with custom orchestration, persistent memory, trace replay, automated evals, and MCP integration.

An experimental Application Object Model for helping LLM agents understand, reason about, and operate real apps.

Production-grade multi-agent workflow orchestrator built with LangGraph, MCP (Model Context Protocol), A2A protocol, and PostgreSQL+pgvector. Features supervisor hub-and-spoke routing, human-in-the-loop approvals, semantic memory, circuit breakers, LLM-as-judge evaluation, and a real-time Streamlit observability dashboard.

Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.