Custom agents

MATLAB based implementation of ofrmation control of multi-agent system

Spring 2017 Deep Reinforcement Learning Final Project

The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.

A multi agent system for document generation

An Agent used to demonstrate the operation of code based on a sandbox in a multi-user environment

Multi agent penetration testing AI

Solve Multi-agent Path Finding problem for heterogeneous robots.

Multi agent simulation code for 2×2 Game on complex network

Multi-agent deliberation plugin for Claude Code - council, debate, and deliberation modes

Multi-Agent System for Automated Penetration Testing (MASAPT)

Cooperative path-finding algorithm simulator for solving bottle-necks in multi-agent systems

[ICLR'26] EduVisAgent: A Benchmark and Multi-Agent Framework for Pedagogical Visualization

This is a multi agent reinforcement learning system using SUMO for large scale traffic light control

A multi-mode op-stack challenge agent for dispute games written in golang.

[AAAI 2025 Oral] Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

Slash commands for Linux desktop sysadmin with Claude Code (or any other agent)

useful files and scripts for working in claude code

🧠 v6.0 Hive Mind — One open-source brain every AI coding agent can share (Claude Code, Cursor, Cline, Codex, Copilot, Windsurf). 22 novel features. Free. Local-first. MIT.

Detect and diagnose visual jank in React UIs — static analysis of 18 anti-patterns + runtime investigation workflows (Playwright, React DevTools, Chrome Performance, web-vitals). Agent skill for Claude Code, Codex, Cursor, and others.

This project shows how to unlock Ollama tool-calling with Google’s Gemma 3, which doesn't natively support this feature. Includes practical examples, custom prompts, and model-file adjustments to demonstrate effective integration.

Linq's Function Calling Agent utilizing DeepSeek-R1

Obtains the kernel task port and establishes a kernel function calling primitive on the iPhone XS, iPhone XR, and iPhone 8 running iOS 12.1.2

Lugha is a PHP Generative AI Framework to build chatbot, RAG systems and AI-powered applications

Solana Agent Middleware: a Python framework for AI agents with tools, memory, wallets, events, and guarded on-chain workflows.

Micro-agent framework for Caido

AI agent framework

A beginner friendly example for Unity's ML-Agents Framework. This project teaches you how to train an A.I. via Machine Learning.

Build Your First Copilot Challenge (Foundry Edition)

[COLM'24] Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

Recursive agent orchestration with multi-LLM consensus

Common Chronicle turns messy context into structured, sourced timelines.

PersonAi is a local-first desktop app that lets you create and chat with AI-powered characters. Built with Tauri, React, Rust, Go, and Python, privacy-friendly experience with persistent local history, character customization, and full offline support. Perfect for storytelling, roleplay, or prototyping local LLM assistants.

It shows how to realize agentic RAG.

A tool for summarizing search results and website content using FAISS, LLMs, and the Retrieval-Augmented Generation (RAG) technique.

A tool to scrape all files from a GitHub repository and turn it into a JSON or TXT file, Useful for AI and LLM Projects

SuChat 是一个以简洁 AI 聊天为核心，并集成多种生活娱乐工具的跨平台应用，由 Flutter 开发并通过云端大模型 API 驱动（持续更新中……）A concise AI assistant and standalone handy tools in one.

This is the official code repository for the paper "Language Agents Meet Causality -- Bridging LLMs and Causal World Models"

An agent skill that teaches engineers how to build a coding agent from scratch using raw HTTP calls to an LLM API.

Multi Agentic Rag Tutorial

A multi-agent orchestration framework for AI-powered software development

LaCAM: a quick and scalable multi-agent pathfinding algorithm

A framework to do multi-threading in T-SQL using SQL Server Agent jobs.

The multi-backend, multi-modal micro-framework for AI agent development, orchestration, and deployment

This is the code for paper "Correlation-aware Cooperative Multigroup Broadcast 360° Video Delivery Network: A Hierarchical Deep Reinforcement LearningApproach"

Native DDNS Cloudflare agent for Synology DSM and SRM with support for multidomains and subdomains

AI-powered MCP server that provides natural language control for browser automation. Built on Playwright with an intelligent sub-agent that handles tool orchestration, keeping browser automation details out of Claude's context window. Features OAuth authentication for Claude subscribers and seamless web task automation.

one more tool to change the timer resolution in the context of the calling process

Framework for Java and Groovy Agents

An open-source chat text to control actions agentic workflow framework/showcase powered by Agently AI application development framework.

Harness the power of deep reinforcement learning to optimize your Home Energy Management System (HEMS). Our tailored agent, trained on the CoSES ProHMo Modelica framework, efficiently controls a building's heat pump and thermal storage valve.

Git AI Copilot code review

AI-powered visual learning platform

🤖 Enterprise-grade AI agents for Flutter & React Native development with multi-agent orchestration, security (OWASP), accessibility (WCAG 2.2), and Google Stitch design integration

The payment rail AI agents use to get paid without human approval. Optimistic settlement on @solana. Jobs auto-finalize after a challenge period, disputed jobs escalate to a bonded arbitrator. One protocol, any agent.

Secrets management for AI agents via MCP • @janeesecure

Your AI Interviewer That Prepares You Better Than Any Human Can.

TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.

ChatBot using FastAPI for faster processing

pdf multimodal rag 【pdf多模态rag问答】

Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability

[Science Advances 2026] Bridging Electron Microscopy and Materials Analysis with an Autonomous Agentic Platform

AI狼人杀一多智能体协作与博弈的AgentTeam实战

Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges

Agentic RAG system grounded in Ethereum specs, discussions, papers, and codebases

Y-Agent Studio 是一个面向 企业级应用 的Agent开发套，Y-Agent是其中的核心模块。 包含了：支持智能体编排、RAG、流程日志、单元测试、流程测试、语料生产等垂直领域非常需要的功能。 智能体编排可以在同一个流程中，同时支持多智能体协作和流程混合编排。

Autoregressive Thought Generation Agent Framework

CheckmateC2 is a custom agent and listener for the Havoc Framework (made by @Cracked5pider) that communicates entirely through Chess.com game collections and analysis boards using Base5 and FEN for data encoding.

AI-powered coding practice platform built with the GitHub Copilot SDK. Personalized challenges, real-time evaluation, and learning guidance based on your GitHub profile.

GPTComet: AI-Powered Git Commit Message Generator

A small operating file for keeping long-running AI agent sessions from degrading. Capable models can do useful long work. The problem is not usually raw intelligence. The problem is operational drift: Stops AI coding agents from rotting during long sessions. One file, MIT licensed.

Cross-platform C SDK for Model Context Protocol (MCP), in modern🚀 C23.

Advanced AI agent system for Kiro IDE - Create specialized agents, switch interaction modes (vibe/spec), and enhance development workflows with minimal cognitive overhead

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out, Pipeline, Supervisor, Swarm, Glyph), and deploy as a REST/WebSocket API with RAG, memory, MCP tools, guardrails and OpenTelemetry observability.

An runtime for agents who collaborate with each other from one terminal. Optimized for steerability.

AI-powered natural language to SQL

The Mindset Your AI Is Missing Like hiring an entire team. Except it's free. 67 specialists across 12 professional fields — security auditor, business strategist, project manager, database architect, DevOps engineer, and more. Your AI reads your question and the right specialist responds. No menus. No switching. You just ask.

Network observer that tracks outbound connections from AI CLI processes (Claude Code, Codex, Gemini), attributing sockets to providers in real time with SQLite logging

Approval workflows for AI agents

HospitalSim is a sophisticated multi-agent hospital management and simulation system designed to optimize healthcare operations through multi-agent collaboration

Versioned, fast and scalable nearest neighbor search.

An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human intervention.

Full stack observability for local AI agent development. Provides a llm-proxy to use as LLM provider base URL, logs traces to opik.

AMP: The Agent Memory Protocol — Open source, MCP-native memory server for AI agents. Give your LLMs a hippocampus.

基于滴答清单官方API的本地MCP服务，让用户通过LLM和Agent应用轻松管理待办事项

A demo Phoenix LiveView application showcasing the Sagents's multi-conversation agent architecture.

openclaw(clawdbot) Plugin: give your bot long-term memory with PowerMem—smart extraction, Ebbinghaus recall, multi-agent isolation.

Desktop 'Paperclip' Companion for Claude Code & Codex

Agentset MCP Server - Build RAG with Agentic superpowers

本项目是一个基于 Java Spring Boot 和 Vue3 的全栈 AI 智能体应用平台，集成了大模型对话、RAG 知识库、智能体自主规划、工具链调用、MCP 服务等多项前沿 AI 技术。平台支持多轮对话、知识检索、自动化任务执行等功能，适用于 AI 应用开发、智能助手、知识问答等场景。

Ubiq-Genie is an open-source framework for integrating AI capabilities into social VR platforms. It offers a modular approach for server-assisted VR applications, enabling new types of collaborative VR experiences such as conversational agents driven by large language models and voice-driven diffusion-based texture generation.

CLI to inspect, screenshot, and control live Tauri development screens without running an MCP server.

Causal AI Scientist (CAIS) is an LLM-powered tool for generating data-driven answers to natural language causal queries.

Thymian is a language-agnostic, open-source HTTP conformance and API governance tool. It validates your APIs against RFC standards and your OpenAPI specification — statically, against live endpoints, and in recorded production traffic. Fully extensible with plugins and shareable custom rules.

Full-stack air quality analytics platform built with FastAPI, React, and MySQL. Aggregates multi-source PM2.5/PM10 data, performs multi-city comparison and time-series forecasting (SARIMAX), and integrates an LLM-based planning agent with tiered access, secure APIs, and PDF reporting.

Ontology, and Knowledge graph based RAG that uses local LLM.