Custom agents

AEC Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction

基于 Django + Vue 的 RAG 知识库问答系统，支持 Agent 推理、知识图谱、Wiki 自动生成和跨会话记忆。

An open toolkit and public dataset hub for collecting, sanitizing, analyzing, and visualizing coding agent traces.

784 AGENT DEFINITIONS · 748 SKILLS · 141 PROMPTS — COLLECTED ACROSS 11 AI PLATFORMS: CLAUDE CODE, CURSOR, ANTIGRAVITY, OPENCODE, GITHUB COPILOT, NANOBOT, NANOCLAW, OPENCLAW, PICOCLAW, ZEROCLAW, AND MORE.

MCP server for debugging Electron apps via Chrome DevTools Protocol. Start/attach processes, capture screenshots, read console errors & network logs, inspect DOM, evaluate JS, and automate UI — built for Cursor and other MCP clients.

BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.

Boss直聘自动化 CLI：候选人列表、推荐牛人、批量发消息、自动打招呼；基于 Puppeteer/CDP，适合 AI Agent 招聘自动化

Production-ready PySpark ETL template for Databricks — medallion architecture, DABs, tests, DQX, CI/CD, and agentic development with Claude Code.

Turn real coding projects into evidence-grounded, just-in-time learning.

Claude Design: AI UI/UX architect. Screenshot to React, Figma components, Tailwind CSS generator. Prototyping agent, design systems, wireframe renderer. SVG icon creator, dark mode toggle, responsive layout tool. Front-end code export, shadcn/ui integration, vector assets, branding assistant.

Uses only the subcriptions you have. Control different agents with agents. Free, local, workspace for AI agents. Let one agent (Claude Code, Codex, Hermes, DeepSeek, Kimi, ...) spawn and drive others over MCP. No API keys, no changes to your Agent.md or Claude.md. TUI, Web UI, CLI, MCP in one package.

Battle-tested operating system for shipping product with LLM coding agents. 17-stage wave loop, two-reviewer gate, dual-document agent memory, full template library. Everything you need to turn agentic coding from vibes into a repeatable process.

The Level-Navi Agent, a framework that requires no training and utilizes large language models for deep query understanding and precise search operations. The repo includes benchmarks, datasets, and tools for assessing LLM performance in web searches

Line bot that checks if a message contains internet rumor.

SemantiClip is an intelligent video processing application that transforms video content into rich, structured written formats. Built with Microsoft Agent Framework, SemantiClip automates the transcription, segmentation, and content generation process - demonstrating agents orchestration with the use of SLM & LLM.

Discord Bot - Track and celebrate birthdays in your discord server!

Hybrid Conversational Bot based on both neural retrieval and neural generative mechanism with TTS.

Kommunicate Android AI Agent SDK

An AI-powered assistant for your company's docs.

商旅-agent-guide | 企业级 AI Agent 学习+实战+面试一体化项目 | Python/Java/Go 三语言 | 200+面试题 | STAR面试稿 | 哆啦A梦漫画

All the class codes, projects, and assignments for the SMIT Batch 2th.

Start Here -- RustChain Bounty Concierge for humans and AI agents. Browse bounties, register wallets, check payouts, automate cross-platform engagement.

A benchmark for evaluating AI agents on frontier research tasks including system optimization and model development.

Mind-aware Multi-agent Management Reinforcement Learning

Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.

This repo contains the code for our paper entitled "Multi-Agent Trajectory Prediction with Heterogeneous Edge-Enhanced Graph Attention Network".

Official python agent for using the distributed hashcracker Hashtopolis

LangGraph adapter for LiveKit Agents

DAYDREAMER goal-based agent

Local TV Extras Agent for Plex

Open Source Agent Execution

Discover how to build agents that can perform actions on websites by combining Amazon Nova Act with Model Context Protocol (MCP).

时下热词追踪Agent 💡，集成多 Tools、TTS、ASR、HeyGem API

VersperClaw: An Agentic Research Workspace that combines search, browser control, coding, and long-session continuity to support end-to-end scientific workflows.

JNC (Java NETCONF Client) is the name of a Java library for communicating with NETCONF agents, and a plugin for pyang (http://code.google.com/p/pyang/) to generate Java classes from YANG models, to be used by the JNC library.

Desktop Tiny Agent is a lightweight, modular desktop intelligent agent framework. It offers plugin extensibility, task scheduling (sync/async), configuration management, and unified logging, supporting dynamic plugin loading for task execution. With an out-of-the-box CLI and examples, it’s ideal for quickly building extensible automation assistants

a chatbot framework based on rails

雀魂游戏实时 AI 指导 / Majsoul-AI-Assistant-MahjongMaster / MajsouI copilot / 雀魂助手 / 雀魂教练 / 雀魂AI分析

Amazon MCP server to search & buy products using the L402

The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.

A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM

Multi-agent (path finding) planning framework

A simple RAG and Function Calling demo based on WPF and Semantic Kernel.

Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.

This repository contains the code for the paper“iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement”

A powerful desktop AI assistant with agentic browsing, listening, coding CLI and editor

VUDA is an autonomous debugging agent that empowers AI models to visually analyze, test, and debug web

【PPT汇报Agent】An AI agent that can present, answer questions, and control slides in real time.

Embeddable AI voice assistant button built with LiveKit

The world’s first science-focused human-AI Agent collaborative discussion community.

< 한 걸음 앞선 개발자가 지금 꼭 알아야 할 클로드 코드 >

这是一个功能强大且易用的MySQL数据库MCP（Model Context Protocol）服务器，让你的AI助手可以安全地进行完整的数据库操作，支持多数据库连接管理、增删改查、事务管理和智能回滚功能。

A small collection of Claude agents with my workflow

A self-hosted web application for managing AI skills, workflows, and contexts with full MCP (Model Context Protocol) integration. Organize, manage, and dynamically load specialized knowledge bases into any AI Agent just by toggling your Skills On/Off in simple local hosted WEB UI.

Multi-agent coordination system for Claude Code with institutional memory

一个用于 AI 虚拟试衣的 Agent Skill。用户可以通过“上传服装图/模特图”或“文字描述”快速生成试穿效果图，并可继续生成多角度素材和展示视频。

🌼 A token-friendly local MCP server for DaisyUI component documentation using their public llms.txt.

Let Claude manage your tastytrade portfolio.

An example configuration of AGENTS.md and a set of skills for AI-assisted game development with the https://defold.com engine.

做证据可信、过程可追、自主优化的长程自动化 AI 科研工具。

A project showcasing how to leverage AI coding assistants (Cursor, Claude Code, etc.) for accelerated NVIDIA DeepStream SDK application development using a curated agentic skill and structured prompts.

AgentTrace is a lightweight observability library to trace and evaluate agentic systems.

EdgeCrab 🦀 A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw — Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters, and built-in security hardening.

A cross-platform AI agent orchestrator in C++ that turns any device — including your phone — into a self-contained, multi-agent automation platform

File-based message queue for local agent-to-agent communication (Maildir-style)

🦙 Opilot: Ollama for GitHub Copilot VS Code Extension – Run Ollama models locally and in the cloud within GitHub Copilot Chat

Curated tools, official sources, OSS, templates, and guides for EU AI Act compliance.

LLM-powered PermissionRequest hook for coding agents (e.g. Claude Code)

AI 智能体专家团队（中文版）— 80+ 个专业 AI 智能体人设，覆盖开发、设计、营销、测试、运维等领域

Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario playbooks. Autonomously plans attack paths, selects tools, and integrates results across phases to adapt the penetration strategy — with human approval gates for high-risk actions.

本地 AI Agent 协作平台 — slock.ai 的本地开源复刻版，由 Cursor CLI 驱动，无需登录，所有数据 100% 本地存储。

WormGPT desktop chat client built with Electron + React and the Groq API.

Commercial real estate AI agent skills for CRE underwriting, due diligence, financing, brokerage, legal and closing workflows - standalone prompts for Claude Code, ChatGPT, Cursor, and other LLMs.

Claude Code skill that enables Claude to extract, analyze, reverse engineer iOS apps

Composable Agent Skills for Polymarket prediction market trading. Paper-trading-first, security-audited. Works with Claude Code, OpenClaw, NanoClaw, Codex, Cursor.

An auditable enterprise sales insight agent with LangGraph, evidence grounding, deterministic guardrails, evaluation, and human review.

Agent for USDT-margined perpetual futures on Binance, Bybit, and MEXC. Combines technical analysis context with an LLM

AI Agent 学习路线与资料库收集

Confidential is the confidential computing stack. We run your AI workloads (inference, training, agents) in hardware-encrypted Trusted Execution Environments (TEEs). You can provide on-prem security and end-to-end privacy guarantees on your off-prem hosted infrastructure. Your data and code stay private. You can independently verify these claims.

OpenTelemetry skills and reference documentation for AI coding assistants - instrumentation patterns, telemetry quality guides, and Dash0 integration

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

Build polished interactive maps and report-ready figures from spatial data with AI agents.

A living atlas of AI companies, products, founders, investors, traffic signals, and research notes.

Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsurf, Hermes and any MCP client.

telegram bot with gpt

AI Disk Cleaner Advisor

The MVC framework for chat apps built on a platform designed for communication systems.

Awesome Multimodal Assistant is a curated list of multimodal chatbots/conversational assistants that utilize various modes of interaction, such as text, speech, images, and videos, to provide a seamless and versatile user experience.

This repository contains a new adversarial training method for Generative Conversational Agents

Simple planner for AutoGPT that can create tasks and checklists to execute commands based on its strategy.

PhysiCar AI - GitHub Codespaces environment for Agent, ROS2 and DeepRacer

面向 iPhone/iPad 的 Python & JavaScript 开发环境。Python 3.13、JS 运行、HTML 预览、语法高亮、分屏编辑、AI Agent（24 个工具）、SSH 服务器管理（终端/SFTP/部署/监控/AI 运维）。Write, Run, Deploy on iOS。

Confidential is the confidential computing stack. We run your AI workloads (inference, training, agents) in hardware-encrypted Trusted Execution Environments (TEEs). You can provide on-prem security and end-to-end privacy guarantees on your off-prem hosted infrastructure. Your data and code stay private. You can independently verify these claims.

This is a repo for studying the application of LLM Agents on Games

Language modeling sft demos

A High-Efficiency System of Large Language Model Based Search Agents