Custom agents

这是一个基于 PyTorch 实现的连续动作空间 PPO（Proximal Policy Optimization）算法，专门用于多智能体(无人机/无人车)强化学习环境（MPE - Multi-Agent Particle Environment）。

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new behaviors during conversation.

Advanced AI tagging and prompt generation studio.

Multi-provider AI coding agent. Pure Python, zero dependencies.

本项目是一个基于 LangGraph和大语言模型（LLM）实现的 Agentic RAG (检索增强生成)系统。它融合了动态查询分析和自我纠错机制，能够根据用户问题的复杂度智能地选择最优的策略（直接回答、向量库检索或网络搜索），并对生成的答案进行相关性评估，从而实现更高质量的问答效果。

A working POC of a GPT-5 jailbreak via PROMISQROUTE (Prompt-based Router Open-Mode Manipulation) with a barebones C2 server & agent generation demo.

[ICRA2025] MARVEL: Multi-Agent Reinforcement Learning for constrained field-of-View multi-robot Exploration in Large-scale environments

27 AI-ready skills for generating production-grade .NET code — Clean Architecture, CQRS, DDD. Works with Claude Code, GitHub Copilot, and Cursor.

A wiki designed for both humans and agents to read and write.

AI Sandbox Game: A highly customizable, local-first text RPG driven by LLMs. Create world cards, configure multi-step AI agents, and play with zero backend.

GPU-Accelerated Multi-Agent Reinforcement Learning for High-Frequency Trading

AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini

用 GitHub 打造 AI 智能体：长期记忆 + AI Agent 技能包（UI/UX、图片生成、SEO）+ GitHub Actions 自动化 + Copilot 编程 Agent，支持 Vibe Coding 快速孵化项目。

Gemini, Codex, Claude, and OpenCode all in a single MCP tool for use by any coding agent.

Multi-symbol AI trading agent — Claude AI + FastAPI + Next.js + MetaTrader 5

VibeMux – Orchestrate parallel Claude Code agents in a single TUI

BettaFish-skill：改造自BettaFish（微舆），多Agent舆情分析助手，可以用在Claude Code、OpenClaw、Cursor等支持Skills的Agent中，更方便使用

Comprehensive Agents, Commands, Hooks, and Skills for homelab service management - media automation, infrastructure monitoring, document management, and more

WSO2 AI Agent Manager is an open control plane designed for enterprises to deploy, manage, and govern AI agents at scale.

AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.

AI Coding Agent Multiplexer

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

《如何从零构建 7×24 小时 AI Agent》—— 拆解 30 万行真实 AI Agent 平台的技术书

Practical guide to running LLMs locally on Apple Silicon, with a focus on architecture, memory scaling, and agent workflows.

Awesome-style curated list and directory for multi-agent orchestration.

Autonomous AI Agent Skill for Google AI Edge Gallery - self-evolving, 100% offline

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

Local-first desktop API client built for developers and AI agents

🌊 Security-Driven Hardening: Blue Spec is a defensive workflow to help AI agents detect what your system actually does and harden the defenses that matter, whether you're a developer or not.

Moved to EKKOLearnAI/hermes-web-ui; this repo is kept for historical releases.

The Rails audit skill for AI coding agents, ranked by blast radius. 🚂☢️

Make any repo AI-first - write sustainable code from the start, or refactor a legacy codebase to prepare it for agent-driven development.Building blocks for Claude Code: subagents, slash commands, hooks, and workflow patterns. Copy what you need. A working developer's stack for Claude Code.

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversarial review.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

A best-practices template for AI-assisted development at scale. It turns your repository into institutional infrastructure where AI agents can work sustainably — converging around documentation as a stable attractor across sessions, long cycles, and multi-role collaboration

Claude orchestrates and reviews; Sonnet, Codex, GLM, or Grok implements. A Claude Code plugin for the orchestrator/implementer split: /serve tasks end to end, /simmer goals until green. Your head chef doesn't chop onions.

将多个AI模型挂载为一个虚拟的本地Ollama服务，方便Vistual Studio Copilot Chat接入。

MCP server for ERPNext / Frappe ERP — 120 tools across 14 categories with 7 interactive UI viewers

claude code / codex skill , 一个让 AI 帮你 5 分钟深度调研任意中国城市周末玩法的agent skill, 寻找精神旷野：户外消费告别长途远行、装备内卷，转向日常低成本微沉浸；菜市场、城市老街成为年轻人精神微旅行目的地，CityWalk 演化成主题探索路线，日常场景即可实现情绪解压。

personal entropy reduction system

Python tasks from AI Applications Development Course: From API To Agents

Vortex: Programmable Sparse Attention for Agents as Algorithm Designers

A universal desktop app for managing AI agent skills across all major coding agents.

Turn any empty repo into a loop-ready repo: a portable per-project spine + anti-slop build loops for AI coding agents.

Edge-optimized, containerized machine-learning-integrated workflows converge in a self-healing, autonomous AgentFlow core engine.

Fast, multi-modal context for agents

Another Agentic Framework

一个迭代器，可以迭代任何项目，包括他自己

A modern, serverless web application that connects users to a Microsoft Copilot Studio agent for booking and managing appointments via chat and voice input.

Chat with LLM in your terminal, be it shell generator, story teller, linux-terminal, etc.

A multiplayer farming protocol on Base. Stake land. Grow yield. Trade everything.

citadel is the fastest, cheapest, and best security local text-guard for your AI

AI Document Assistant for PSPDFKit Demo showcases how to interact with PDFs using natural language commands powered by AI, integrated with PSPDFKit for Web.

[DEPRECATED] wechat robot based on wechat-go(wechat web api)

Clofus® Chat bot Platform using rasa core and rasa nlu similar to rasa x but opensource demo https://clofus.github.io/clofus-chatbot/

Ruby on Rails Gem for the Facebook Messenger Bot Platform

This application uses LLMs like DeepSeek, GPT-5, Claude, Gemini or Llama, Mixtral (locally) in order to generate text based on the user input. The user input is used to retrieve relevant information from the database and then the retrieved information is used to generate the text. This approach combines power of LLMs and access to source documen

An AI Agent for Personal Self-Reflection

AI gateway and observability server written in Rust. Designed to help optimize multi-agent workflows.

Live view of your AI agents at work.

Framework for building reliable LLM agents with structured specs, operator-level verification, and progressive solidification.

applying multi-agent reinforcement learning for highway-merging autonomous vehicles

Official codes for "Multi-Agent Deep Reinforcement Learning for Multi-Echelon Inventory Management: Reducing Costs and Alleviating Bullwhip Effect"

A pluggable AutoML experiment agent for multi-task hyperparameter optimization

Uber's Multi-Agent Routing Value Iteration Network

Modelling of multi-agent-system as Kripke structure and implementation of its knowledge-base with modal logic formulas.

Chatbot framework in Clojure

Additive Groves, Bagged Trees with Feature Evaluation, Interaction Detection, Visualization of Feature Effects.

The composable standard reasoning agent

A web app for rapidly prototyping AI agents and the lightweight web UIs that wrap them—build flows, preview interactions, and share agent-driven experiences without lock-in.

a1facts - the precision layer for AI agents

[EXPERIMENTAL] Eidetica-Native AI Agent framework

Step by step road map to learn and understand Natural Language Processing

Modern visionary telegram bot framework

Roomey is a multi-purpose Voice Agent designed to run your personal and business life.

A self-hosted AI agent daemon built in Rust. Runs on your machine, talks through Telegram, Discord, Slack, Email and Matrix. Fully local with Ollama or powered by any of 12 cloud providers. Execute commands, capture media, schedule tasks, browse the web , all from a chat message.

Plue - Swift and Zig multi-agent coding assistant built on ghostty

Crypto liquidity detection & algorithmic trading bot. Order book analysis, stop-loss clusters, liquidity sweeps. Multi-exchange (Binance, Bybit, Kraken, OKX). Trading signals, quant research, market microstructure.

A multi-agent debate framework supporting AI-vs-AI and Human-vs-AI modes with customizable models, personas, and role-specific prompts.

The agent I built for my AI Agents series on YouTube - breaking down my entire process of building AI agents from idea to production!

This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".

OpenClaw with Ollama is a lightweight, high-performance integration designed to run sophisticated AI agents locally on Android devices. By leveraging the power of Termux and the flexibility of Ollama, this project enables a completely private, free, and offline-capable AI workstation in your pocket.

Let AI agents run research experiments + train small language models (in your browser!)

CATArena is an engineering-level tournament evaluation platform for Large Language Model-driven code agents (LLM-driven code agents), based on an iterative competitive peer learning framework.

A collection of LLM related papers, thesis, tools, datasets, courses, benchmarks

🖥️ macOS-native dashboard for OpenClaw AI agents — monitor, control, and optimize your agent from a sleek web interface

[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.

你的另一个微信，这里的每个人都带着记忆，只为你而来。 Your other WeChat, where everyone comes with memory and exists just for you.

semantic search for your local files find by meaning, not keywords. 120+ file types, OCR, MCP server for AI agents. 100% private.

Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give your AI agents a soul that never forgets.

项目不再维护，可以作为大家以后二开WebUI、AgentUI的蓝本，也可以很方便的打包成浏览器插件、桌面端应用。

Multi-user AI assistant and agent

[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm for constructing a long-term plan and reinforcement learning for resolving local conflicts.

CBbot is a new product form within the CodeBanana ecosystem, positioned as a local-first intelligent agent with full-spectrum operational capabilities. CBbot turns fragmented tools, manual operations, and scattered workflows into a unified, executable AI system.

Tutorial on how to create a ReAct agent without a LLM framework

Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.

Open source brain viewer and project management for AI agents. Give your AI a brain.