Custom agents

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

Function Calling Mistral 7B. Learn how to make functions call for open source LLMs.

Multi-agent system (MAS) hijacking demos

The conceptual architecture and governance whitepaper for ChronicleCore, an enterprise-grade Multi-Agent orchestration framework.

The purpose of the "Meta Agent with More Agents" project is to dynamically solve complex queries by breaking them down into smaller tasks and assigning each to specialized AI agents. The Meta Agent coordinates the process, leveraging a ReAct Agent for tool-based tasks and a Chain of Thought Agent for reasoning-based tasks. The system's flexibility.

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

💰 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

Skills Manager 是一个基于 Tauri 构建的Windows轻量托盘应用，用于集中管理本地 AI agent skills。

Implementation of Evo-Memory style learning for LLM agents. Agents learn from outcomes, refine strategies, and get smarter with every task. 🚀 Features: Experience-driven memory architecture Semantic search + context synthesis Self-improving agents

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

A simple PolicyKit authentication agent for XFCE

Official Code Release for "Training a Generally Curious Agent"

这是一个用于claw.cloud部署 Hysteria2 + Nezha Agent 的轻量级 Docker 镜像。

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.

[ACL 2026] LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark

OneKey Agent Gateway access to Commercial APIs, Skills, MCPs Build once and Ship 10× faster. For devs & builders, A unified API registry to serve and distribute across all agent formats—CLI, REST, MCP, and Skills—eliminating multiple builds. Access 30+ categories like search, image, finance, and 3D Rendering, register, and monetize APIs 10× faster

Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.

iClaw is a local, native macOS 26+ AI agent

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

Free AI skill pack for senior UX and Product Designers. Runs on Claude Projects or any LLM. Strategic, Direct, and Provocative reasoning modes. Copy, paste, done.

MCP server for the X (Twitter) API -- give AI agents the ability to post, search, read, and engage on X

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

The LMOS Runtime facilitates dynamic agent routing and conversation handling in a multi-tenant, multi-channel environment.

[ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Light-weight reasoning-loop agent library for JavaScript

A realtime drawing game showcasing the use of LiveKit data capabilities in an Agents-based app.

Terminal Agent is a DevOps-focused intelligent terminal assistant for system diagnostics, application deployment, service monitoring

A data construction and evaluation framework to quantify privacy norm awareness of language models (LMs) and emerging privacy risk of LM agents. (NeurIPS 2024 D&B)

一个简易的桌面agent应用

CLI for AI-assisted manual code review

🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.

Python SDK for Agentic Prediction Market trading

The control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks, 4,000+ adversarial payloads. Discover. Assess. Test. Monitor. Comply.

Research Agent for multi-hop reasoning QA — 1st place in Alibaba Cloud Data+AI Global Competition (College Track). Built on PAI-LangStudio with Qwen models, featuring ReAct reasoning, dual-engine search, and web content extraction.

Evaluate your agent memory on real-world dialogues, not LLM-simulated dialogues.

ambient memory agent, your machine's psyche

(▰˘◡˘▰) - AI Tamagotchi on Raspberry Pi. Agentic life-form with an E-Ink face

A brief introduction to agentic coding principles and practice

Skills for AI agents.

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

An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core. Use the results in an agentic loop with your favorite AI assistants (Amp/Cline/Cursor/GH Copilot) and let them fix a11y issues for you!

60 self-contained, Dockerized vulnerable web applications for evaluating AI-powered penetration testing agents. Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby) across diverse vulnerability classes from basic injection to multi-step exploit chains.

Multi-agent collaboration extension for pi — task decomposition, dependency management, parallel execution, TUI panel

Agentic closed loop with async capabilities

Save coding agents' conversations in Git Notes, automatically

a curation of questionably-useful coding agent plugins

[ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents

Agent-first Rust/Axum backend harness for SDD-driven Clean/Hexagonal/DDD services, ECS-style runtime composition, counter-service reference chain, progressive local→VPS→k3s topology, and entropy-resistant agent context/naming grammar.

credit score for context

AI Agent Orchestrator for Claude Code

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

A production-ready, all-in-one Docker image designed for AI agents and autonomous systems that need to execute code across multiple programming languages.

Patterns of Multi-Agent System Architecture

OpenFR：Multi-Agents for financial research

Best DX + AX for Building the Best UX. An ultra-lightweight (~2.5KB) pure vanilla JavaScript framework with signal-based reactivity and built-in AI agent support.

A desktop coding agent built with Mastracode and Electron.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

Goal-Driven agent for long-running tasks, docker-isolated workers, intelligent task decomposition, and autonomous execution

Embedded single file SQL database written in Golang

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

[ICLR 2026] "When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms"

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

Concrete Multi-Agent Path Planning Enabling Kinodynamically Aggressive Maneuvers (npj Robotics 2026)

Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI

🦞 Low-latency, limited-context AI harness for private on-device homes.

Governed infrastructure for internal tools and AI agents

Spring Boot integrations for Amazon Bedrock AgentCore

A JetBrains IDE plugin that integrates OpenCode — the open-source AI coding agent — directly into your development workflow.

AI Development that stays consistent across agents and sessions. Plans are checked, work is verified, and the progress is tracked in repo.

Local-first, AI-assisted circuit design tool. Wire components in a 3D view, describe what you want to build, and the AI agent writes the firmware and simulates it all before you touch a chip.

Save 47% on Manus AI credits automatically. Zero downsides. Pays for itself in ~27 prompts. Free MCP Server (PyPI) + $12 Manus Skill bundle with Fast Navigation (115x speed boost).

Run your entire company with Claude Code. 15 AI Agents + 5 Skills + Approval Pipeline. Battle-tested in production for 1+ year.

This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.

大模型算法工程师、大模型Agent开发工程师面试：常见题目和答案

🦞 LobsterPress（龙虾饼） - Cognitive Memory System for AI Agents 基于认知科学的 LLM 永久记忆引擎

Multi-Agent Autonomous Medical Collaboration System

Voice dictation menu-bar app for macOS. Press a hotkey, speak, transcript appears at the cursor. Whisper runs locally via WhisperKit on Apple Silicon — no audio, text, or telemetry leaves your Mac. MIT, Swift.

Claude agent skill: Generate high-converting video ads from any product URL. Standalone creative frameworks + Creatify API automation.

Đây là bộ SKILL, RULES, COMMANDS do Anh Tester xây dựng dành riêng cho cộng đồng Tester để thiết lập AI Agent trên Claude Code hỗ trợ kiểm thử phần mềm.

Web dashboard for the pi coding agent — multi-session chat, file browser, doc collaboration, terminal, and more

Claude Code skill for AI persona panels, virtual customer research, and concept testing.

Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.

Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories

AICodePilot is an AI codebase understanding and development assistance system based on LLM Agents, designed for programmers. It supports codebase analysis, semantic code retrieval, code Q&A, log analysis, tool calling, and development assistance.

X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent

Multi-Agent works on native GUI desktop. Supports skills and IM channel, build-in a IDE for light development. Built on the shared piscis-engine kernel.

AutoApply AI is an intelligent system designed to streamline your job search. It automates finding relevant job postings, crafting personalized resumes and cover letters using AI, and assists with application submissions, helping you land your dream job faster.

A general-purpose AI agent harness.

A shopping skill for AI agents, powered by the Universal Commerce Protocol.