Custom agents

Allows LLM agents to control a local chrome instance without taking screenshots

UAV-based Cellular-Communication: Multi-Agent Deep Reinforcement Learning for Interference Management

Image classification using reinforcement learning and multi-agent system

A configurable Multi-Agent System engine for content production pipelines

Aiming at the problem of the traffic efficiency of intelligent networked vehicles passing through unsignalized-intersection in the future smart cities, this project proposed a Progressive Value-expectation Estimation Multi-agent Cooperative Control (PVE-MCC) algorithm based on reinforcement learning. The algorithm takes the intelligent networked vehicles as the research object and designed the reward function for the optimization objective from the three aspects of traffic efficiency, safety, and comfort.

Personal Health Insights Agent (PHIA)

A Pi-Agent extension that supervises the coding agent and steers it toward a defined outcome.

JVM runtime class loading protection agent.（JVM类加载保护agent）

가짜연구소 10기 'Agent is all you need'

Extensions, skills, and themes for Pi coding agent

Simple workflow for agent coding with skills

Agent to automatically update your WSL2 resolv.conf when using a VPN

利用langgraph重构hello-agents项目

Build Agents That Recall What Matters. Systematically engineer relevant context from chat history & business data. (Go SDK)

Make agents prove that their code is correct.

Sage — X content agent for OpenClaw. Voice calibration, tweet drafting, reactive takes, thread writing, trend scouting, feedback loop. Self-installs in 5 minutes.

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

Robust skills for Agents

Fork your conversation into an independent side chat while the main agent keeps working.

An extensible java agent framework that instruments (modifies the bytecode at class loading time) programs running on the JVM, with the purpose of capturing method invocation events (start, finish, errors ...) and notifying custom listeners.

The official GitHub page for the paper "Agent Systems with Harness Engineering"

从嘉靖帝学习的极简主义Agent团队管理，免去上朝和微操

Runtime intelligence system that makes MCP servers debuggable, testable, and safe to run in production.

Performing a RAG (Retrieval Augmented Generation) assessment using voice-to-voice query resolution. Provide the file containing the queries, ask the questions, and receive the results via voice.

Chatbot samples for Webex Teams built with Botkit

Lighter, cheaper and faster RAG toolkit (Graph RAG) supported by TargetPilot

💰 Autonomous AI stock trading agent running on GitHub Actions

This repository contains the code for the LangGraph course: "LangGraph in Action - Building Autonomous AI Agents"

Offline Multi-Agent Reinforcement Learning Implementations: Solving Overcooked Game with Data-Driven Method

LLM as Interpreter for Natural Language Programming, Pseudo-code Programming and Flow Programming of AI Agents

A full-stack EdTech system for generating, auditing, and managing outcome-aligned assessment questions using Bloom’s Taxonomy, featuring a FastAPI backend, PostgreSQL persistence, and a React-based dashboard.

The native AI Agent framework for Bun. Build local-first, bare-metal agents with embedded vector search and instant API deployment. 🚀

Automate user story creation, in a format suitable for AI agents.

这是一个面向 LLM Agent 的知识库脚手架，用于把原始资料逐步编译成可维护、可交叉引用、以中文为主的 Markdown Wiki。

Durable Multi Agents is an attempt to make use of Azure Durable Functions with Semantic Kernel to build Multi-Agents workflows.

[WWW demo 2026] TrustResearcher: Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration

Pinpoint Go agent

NAIL is an agent that plays text-based interactive fiction games.

A simple example of how MPESA works. Works with all 3 types of customers i.e. Agents, Merchants and Subscribers. Allows you to configure a tariff and apply it to transactions. The project follows DDD principles.

Agentless Lite: RAG-based SWE-Bench software engineering scaffold

A persistent runtime for long-lived LLM agents

iClaw is a local, native macOS 26+ AI agent

[T-Cyber 2020] Cooperative Pursuit with Multi-pursuer and One Faster Free-moving Evader

Operating discipline for AI coding agents - persistent memory, enforced workflow, recorded decisions.

Your personal assistant driven by agentic CLIs

Security Scan orchestrator for AI Agents 🎯

[NeurIPS 2025] A multi-agent framework that leverages LLMs to simulate socio-economic systems

Multi-agent pipeline for automated SEC 10-K / 10-Q investment research

Light-weight reasoning-loop agent library for JavaScript

一个用于获取B站视频内容便于 Agent 解析的 SKILL

这个仓库主要用于记录以MetaGPT为基础的Agent开发理论学习记录

Talk to AI about your Logseq notes.

One prompt. Full delivery.

Launch Koishi from your Android devices

SQL-like query language and CLI for Qdrant vector search engine

Creo il mio Trading AI Agent

Native AI agent harness — for agents, by agents. Single binary, zero dependencies.

Security guardrails for AI coding agents. Prevents accidental file operations outside working directory.

Drop-in SDK for adding continual learning and long-term memory to any LLM agent.

My version of an LLM Websearch Agent using a local SearXNG server because SearXNG is great.

MongoDB Agents with Google ADK

ElizaOS plugin allowing agents to connect to MCP servers

ambient memory agent, your machine's psyche

AutoCodeAgent - An innovative AI agent powered by IntelliChain, Deep Search, and multi-RAG techniques

A Benchmark Dataset for Collaborative SLAM in Service Environments

CoGames is a collection of multi-agent cooperative and competitive environments designed for reinforcement learning research.

An experimental SDK for adding agentic memory and learning in a pluggable way

ARC Relay — WebSocket relay server for agent remote control by Axolotl AI

🏢 Pixel-art virtual office dashboard for OpenClaw agent sessions. Visualize your AI workers in real-time.

A customizable MCTS planner with advanced featured tailored to multi-agent simulations and emergent narratives.

Software repo for Team Expander Agent (Oregon State U., Institute for Systems Biology, and Penn State U.)

Local AI-powered code review agents for Claude Code

A modular, high-performance Retrieval-Augmented Generation framework with multi-path retrieval, graph extraction, and fusion ranking

A cross-platform desktop AI assistant that lets you translate, rewrite, summarize, and brainstorm with just a hotkey.

We introduce WirelessAgent, a novel framework that harnesses large language models (LLMs) to create autonomous AI agents for diverse wireless network tasks.

Audit agent skill definitions for security, completeness, and compatibility across Codex, Claude Code, OpenClaw, and more

FxChartAI AI-Agent Trading EA is an open-source MQL5 Expert Advisor for MetaTrader 5 that trades using signals from FxChartAI. It employs trend confirmation, candle tail/trendline analysis, and dynamic order management. Free for personal & commercial use. Contributions welcome.

Family-aware evolutionary alpha mining with LLM-guided symbolic hybridization.

ICLR 2026: Agent-X Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks

Browse, search, and export your Antigravity AI conversations — VS Code Extension

AI Agentic API Testing Platform - Automated testing with specialized ephemeral agents

A desktop coding agent built with Mastracode and Electron.

A Thai token optimization tool for AI coding agents that keeps commands, code, and technical details accurate.

基于Golang的LLM-MCP-RAG的小agent demo

GNS3 Copilot is an intelligent network automation assistant that combines the power of AI with GNS3 network simulation platform. It allows you to manage and configure network devices using natural language commands.

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

📝 An AI-powered document analysis app that turns long, complex documents into summaries, key insights, analytics, and contextual conversations, helping people understand and work with information in seconds instead of hours.

Enhanced note taking for AI Agents with supervision.

🐾 ClawPilot — your OpenClaw copilot. Security-first agent skill for AI coding assistants. Supports 14+ chat platforms.

Clarity is a software design tool for AI-native developers and coding agents.

This is AI implementation (not official) of the DreamGym framework from the paper "Scaling Agent Learning via Experience Synthesis" (arXiv:2511.03773).

A lightweight agnostic agentic framework

Shared config, skills, and update scripts for Claude Code, Codex. Not more custom and new skills, but combined best practices in the community.

FastGPT plugin system. Provide model presets, system tools and other extended functions for FastGPT.