GitHub agents

Standalone MCP server: web search, social media search, web fetch tools for Claude Code / Pi agent

An AI agent that lives on your computer and does the work you ask for, in plain words — from writing code to running your business busywork. Local, one command, any model.

An MCP server that allows users to dynamically add custom tools/functions at runtime

Free, Open-Source Playground for AI-to-AI Conversations

AI-powered prompt optimization hook for Claude Code. Transforms simple prompts into comprehensive, structured instructions using Claude Opus 4.6's advanced reasoning capabilities.

怎样利用claude skills 简单的实现一个适合自己的“微舆”？适合自己的简单“微舆” 。社媒+深度调研 2个skills 合体 的 agent智能体：AI启动了 Web Search 和 via TikHub （社交媒体）进行深度调研 ，2个skills都正常调用了。 2个skills 混合在一起合体使用

[ICASSP 2026] Agent4Debate is a dynamic multi-agent framework that leverages LLMs to achieve human-level performance in competitive debate by dynamically coordinating specialized agents to mitigate hallucinations and enhance competitiveness.

The source-available AI agent operating system

Collection of LLM system prompts, agentic personas, cognitive frameworks & prompt engineering experiments

Automatos AI: Open-source platform for advanced context engineering and multi-agent orchestration in enterprise automation. Built on frontier research in RAG, vector embeddings, cognitive tools, emergent symbols, and neural field theory—powered by FastAPI, Next.js, and PostgreSQL.

My forkable Claude Code setup with sync feature

Bitwig Controller Extension that provides an MCP Server for AI Agent control

Anthropic's Advisor Strategy as a drop-in DeepAgents middleware

Thinking in the Human · Processing in the AI · Truth in the Documentation

AI Agents for Academic Writing. Ingests PDFs or markdown → outputs publish-ready LaTeX with verified citations and TikZ diagrams. One click.

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

OpenLLM Monitor is a plug-and-play, real-time observability dashboard for monitoring and debugging LLM API calls across OpenAI, Ollama, OpenRouter, and more. Tracks tokens, latency, cost, retries, and lets you replay prompts — fully open-source and self-hostable.

A smart multi-agent system to turn prompts into GitHub PRs

Multi-agent reconnaissance skill for Claude Code + Obsidian

Secure multi-platform AI skill installer — scan before you install. 49 agents, 12 plugins, 41 expert skills.

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

This curated list focuses on tools and frameworks for building AI agents

An AI-powered research platform that transforms how you conduct research

Cloud-native AI Agents orchestration platform for zero-human organizations

Autonomous SOC layer for Wazuh using OpenClaw agents with MCP . Auto-triage alerts, correlate incidents, generate response plans with human-in-the-loop approval. Evidence packs, Prometheus metrics, Slack integration.

Autonomous background agent that consumes unused Claude Max quota to explore, audit, and improve a codebase — communicating with its human via Telegram and a shared mission queue.

AI-native development environment for orchestrating agents

On-Call Copilot is an open-source multi-agent AI system built on Microsoft Agent Framework and Agent Services v2 Hosted Agents that automates incident response. It runs four specialist agents concurrently Triage, Summary, Comms, and PIR, returning root cause analysis, a plain-language narrative, Slack and stakeholder update

基于 Openclaw & Claude Code Multi-Agent 架构的多平台智能内容营销中台，告诉他一个主题，闲鱼/小红书/B站/抖音多平台内容自动智能生成与发布。

Autonomous GUI agent — give it a task, it operates the desktop. Visual memory, one-shot UI learning. Built for OpenProgram.

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, and secure governance. ACP Openclaw, Gemini CLI, Opencode

Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

🤖 基于多智能体的A股交易分析系统 | AI-Powered Trading Analysis with Multi-Agent Architecture | 支持技术分析、基本面分析、风险评估

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Model Context Protocol (MCP) server that connects AI agents (Claude, Cursor, etc.) to Wolfram Mathematica for symbolic computation, visualization, and notebook manipulation.

SketchUp meets AI Agents

Memory hygiene skills for Hermes Agent — dreaming (3-phase consolidation)

An Android-native autonomous agent that uses vision-language models to see and operate your phone — no PC or ADB required. Inspired by X-PLUG/MobileAgent.

《从0开始构建 AI 智能体》 一本带你亲手打造属于自己的AI Agent 的实战书

Learn how to write code-based agents using Python, JavaScript and well-known industry standard frameworks. Learn how to deploy your code-based agent to SAP BTP, Kyma runtime, orchestrate them using Joule and integrate into the SAP ecosystem.

Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.

OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.

Zooid is an open-source, self-hostable chat app for collaborating with AI agents alongside your team.

Self-hosted GPT Image / OpenAI-compatible WebUI for text-to-image, image editing, reference-based generation, and multilingual creative workflows.

Private LLM/RAG platform in one command for NVIDIA DGX Spark / GB10 (arm64). Validated on real hardware.

🦞 AI 量化交易系统 — 37 因子选股 · 8 层风控 · 同花顺数据大屏 · 全自动盯盘

一个基于多智能体协作（Multi-Agent）深度研究系统，能够将宏大的模糊课题自动拆解，通过并行联网搜索、智能体内部审查与自纠错，最终撰写生成包含严谨数据、文献来源指向及可视化图表的深度研究长文。

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

:memo: Simplified and open note repo

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

Project-based Claude CLI session manager with automatic tmux setup and persistence

Official skill registry for ZeroClaw — community-contributed AI agent skills, tools, and workflows

Openclaw AI Polymarket Trading Bot — TypeScript bot built with 🦞 Openclaw AI agent. Predicts crypto price on Polymarket 5m BTC Up/Down markets and tracks results (paper or live) and automatically executes trading according to the prediction result.

Lunon Deep Research: an AI research agent built for institutional-quality analysis. Evaluated on DeepResearch Bench.

Download OpenMontage - world's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.

An Agentic based User-testing pluging for claude code and other AI tools, which helps developer get feedbacks from virtual user to quickly improve their products

AI Skills & MCP marketplace - community-curated skills, MCP servers, and agents for Claude Code, Codex, Cursor and more

Personal agentic assistant built for thinking work

一份 OpenAI API 的中文翻译

The first operating system for AI agents — run heterogeneous agents as one governed, memory-driven, production-ready organization.

Multi-Agent Indonesian Fintech Fraud Detection Platform powered by Xiaomi MiMo V2.5 — QRIS, phishing, invoice fraud, WhatsApp scams

LSAP (Language Server Agent Protocol) is an open protocol that defines how AI coding agents interact with Language Servers

一个面向本地代码项目的桌面 Agent 工作台，把 Claude Code、OpenCode 和 Codex 放进同一套桌宠式界面里。

Memory-native AI agent runtime: Rust gateway + React dashboard + Python Operator + Kumiho graph memory

使用AI Agent创造ICPC风格的题目

A curated collection of actuarial AI case studies covering machine learning, generative AI, agentic AI, and more, designed to support actuaries in applying AI to real-world problems.

🎯 First Yandex Direct (API v5) skill for AI agents. PPC audit, campaign management, optimization. By Nick Serebrov & Kobe 🐍

The spend meter and budget gate for AI voice agents. Meters STT + TTS + LLM + telephony per call, out of the box (Pipecat, LiveKit — Python & TypeScript). Hard-stops the next turn before it crosses your ceiling. Local, no account, no telemetry. Built by Floe — cost controls for Voice AI.

PyProc MCP turns public SPSE/Inaproc procurement data into MCP tools that can be used by LLM clients (Claude Desktop, Continue, Cursor), AI agents, automation workflows, Python scripts, and command-line users.

AI agent skills for social media automation — post to 10 platforms, LinkedIn analytics, content calendar. Install: npx skills add publora/skills

Agent Skills · 橙皮书系列 · Claude Code Skills 系统完全指南

A 30-day public U.S. stock challenge: follow a 5000 HKD 🦞 claw through live market days.

Açıklama: Self-evolving Hermes agent that writes, tests, and publishes reusable Skills autonomously. Uses Memory + Skills + Atropos RL.

22+ agentic skills for Antigravity IDE — slash-command workflows that automate code reviews, debugging, UI/UX design, security audits, testing, release management, and documentation.

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

Open, agent-agnostic MCP server exposing macOS computer use to any MCP client (Claude Code, Cursor, Codex, …). Background-safe, works on every app.

Swift-focused AI agent skills for iOS and macOS: build, debug, simulator, SwiftUI, Xcode, App Store workflows. Part of Plug'n Skills.

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workflows.

Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation

Paper list for "From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms".

Local MCP coding agent for ChatGPT Web: run files/commands on your own machine via the OpenAI Secure Tunnel, with a Windows tray app and metrics dashboard.

Agent token and task monitoring, thousands of pet avatars, cross-platform support, and compatibility with popular AI agents. 一眼查看 Token 与任务状态，海量 Petdex 形象可选，支持 Windows/macOS/Linux、ESP/Wio Terminal，兼容 Cursor、Codex、Claude、Windsurf 等主流 Agent。

IBL AI Agent helps you use a coding agent such as OpenAI Codex to analyze International Brain Laboratory (IBL) data.

12 executable AI agent skills for competitive strategy analysis, extracted from Michael Porter's Competitive Strategy. Five forces, competitor profiling, strategic groups, market signals, generic strategies, competitive moves, and industry-type playbooks — grounded in Porter's original frameworks.

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

A collection of skills for agentic LLM tools

Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).

Ready-to-use AI agent skills for e-commerce intelligence. Product research, keyword optimization, competitor analysis, pricing monitoring, patent risk assessment, market trends, and platform-specific tools for Amazon, TikTok Shop, Shopify, Temu and more.

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

基于用户意图进化的智能 Agent 助手平台，目前主要支持文件解析、Excel 数据分析、合同审查、知识库检索、报告导出与自定义技能。

并发调用本机 Grok 4.5、Kimi K3 与 Claude Code，带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compression.

One command → full AI engineering team. Transforms Hermes Agent into a 9-role development organization with Kanban coordination, per-profile authority enforcement, and PAUL-inspired workflows.