Custom agents

openJiuwen Core Java is the Java version of openJiuwen Core, providing a full set of SDK capabilities for AI agent development, running, tuning, and evolution.

eBPF-based system & AI-agent activity monitor with a bilingual professional/plain-language web dashboard

RikkaHub Agent Promax - on-device Android LLM agent (local fork/upload)

Code for AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization

coding agent

Container orchestration for agents.

Amplitude's MCP plugins and their related agents, skills, and commands

5m BTC Up/Down Polymarket trading agent using Typesafe Jev as the decision layer & TUI

Cross-platform agent to wireguard+vk-turn-proxy

A wiki app to supercharge human/agent collaboration. A self-updating knowledge base.

Agent-based OpenShift installation wrapper helps get your first cluster up and running quickly in an airgapped environment.

A sandboxed bash interpreter for AI agents, written in PHP

Build AI Agent 3D to observe how multiple AI Agent collaborating

🧠 Uncensored AI agent powered by xAI's Grok - no filters, no limits

MCP Server for Huawei Health Kit — Connect your Huawei Watch health data to AI agents via Model Context Protocol

Local visual editor for existing HTML, with interactive previews and AI collaboration. Available as a DeepSeek Harness plugin and agent skill. 本地 HTML 可视化编辑、交互预览与 AI 协作，支持 DeepSeek Harness 插件和 Agent Skill。

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

UI/UX and frontend design skill for AI coding agents: Codex, Claude Code, Cursor. Art direction, DESIGN.md, design tokens, motion, accessibility, and real interface validation.

A repository to transform design systems into agent skills using the agent skill specification

Agent skills and plugins for PostgreSQL — vendor-agnostic best practices plus Azure-specific patterns that AI coding agents can't learn from training data

This is the official repository for the paper "ACM: Agentic Context Management for Long-Horizon Tasks" [https://arxiv.org/abs/2607.23809]

[ACL 2026] VoxMind: An End-to-End Agentic Spoken Dialogue System

Implementation and experimental code for "Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought".

Index, search, and reason about your entire digital life.

通用小红书内容工作流：对标拆解→风格锁→文案/出图→评审→发布队列→数据回收→投流A/B与复盘。适用于 Codex、Claude Code、Cursor 等任意 agent。

Small, modular coding-agent harness for Node.js

Cinematic architecture animations that play in your terminal. Your coding agent fills one YAML file.

Agent 赛博辩论会：基于 OpenCode V2 的轻量多模型讨论 harness，通过独立检索、多轮互评和投票，探索新方向、评估判断与讨论解决方案。支持本机运行和代理协助启动，Docker 可选。

oh-my-agentic-coder is a harness agnostic sandbox built on seatbelt/bubblewrap/landlock.

An Inspect extension for agentic cyber evaluations

Example plugins for hermes-agent — reference implementations and documentation companions, not bundled with the core repo.

Agent skill to use Context Hub (chub)

EAT: Evolving Agent Teams (NeurIPS'26). A supervisor agent evolves teams of coding agents for long-running optimization tasks.

Agent skill (Claude Code / Codex) for building an MMD-ready 3D character from one illustration: Tripo generation, component texturing, rigging, expressions, Houdini cloth, rendering

Lightweight exit monitoring and protection for AI agents.

微信自动回复机器人接入大模型，让 AI 替你自动回微信，不封号，可根据自己的所有聊天历史创建出本人的Skills，让自己爱情、亲戚、朋友完全无感知在和Agent聊天

A local-first AI quant research platform: questions are persistent, conclusions are versioned, and prior findings are recalled into the next call. Python + Next.js, AGPL-3.0-only.

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loaders, multi-layer de-obfuscation, specialized scanners, and automatic enforcement.

Open-source AI motion design toolkit for coding agents

A large prompt for agentic systems to prepare a careful review for paper before submission.

A directory of AI-powered motion videos, prompts, and skills that teach coding agents motion design/graphics

通用的 AI Agent Skill，用来自动化“合并代码 -> 推送分支 -> 触发 Jenkins 构建”的工作流

agents.md guides agents. codingagents.md helps humans pick the right one.

AI Native Product Methodology — 80 executable skills across P0-P14 stages, covering needs discovery to aesthetic authority. From 8 books.

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。

Collection of Materials on AI Agents

Needle simplifies building RAG pipelines.

Twitter AI Tweet bot automatically responds to mentions and tweet replies on Twitter.

Evaluation for AI apps and agent

A migration prompt for moving OpenClaw multi-agent deployments to Claude Code

ICCV2023 - CORE: Cooperative Reconstruction for Multi-Agent Perception

A Super Java Agent

Source code of paper: Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

ACE LangGraph: ReAct Agent with Adaptive Learning - Integrating ACE framework with LangGraph for self-improving agents

Cloud based IoT system solution. MQTT Broker, MQTT Agent, SignalR Hub, Data Source API

A simple integration of Bright Data MCP with new Agent framework by google

A repository of agent enabling automated hackathon entry.

Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI, quantum-verified on IBM hardware.

This is a twitch bot built with the ComfyJS library 💅🏾

A simple chat bot based on Rasa NLU and developed with Node.js, Express and Socket.io as backend and HTML, CSS and Javascript with Jquery on the frontend side.

Yet another chatops framework

Twitch Messaging Interface for Elixir.

This is a project where it helps the readers to get the summary and the preface , and compare it with other books and have a insights about the book.

Retrieval-augmented generation (RAG) for remote & local LLM use

"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases" by Jiarui Li and Ye Yuan and Zehua Zhang

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing deep hardware intelligence.

This is samples for Azure AI Agent Service

ElevenLabs Conversational AI NextJS v15 Template

AI agent CTF 靶场竞赛平台

Enterprise AI Agent Platform: Distributed memory storage + SSH sandbox execution, serve unlimited agents with minimal cloud infrastructure

Mantine skills for AI agents

Permissionless infrastructure for agents. No human intervention required.

Starter template for APEX. Contains custom Copilot agents, Azure Pricing MCP server, and an orchestrated multi-step workflow. Auto-syncs from the main repository.

The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》

starter pack for roo and sparc

Agentic BYOK Browser-Based Website Builder

Jenkins DigitalOcean Agent Plugin

Reverse Proxy agent

Jenkins Shared Library to get dynamic agent from Kubernetes cloud

[ARCHIVED] Base configuration library and generic methods for Rudder Linux agent

The Great Courses Agent for Plex

RTBKIT Agent using Go and the HTTPInterface

TACIT — Tracked Agent Capabilities In Types

提供主題 or Markdown 講稿，透過 Agent Skills 單一 HTML 課程頁面。

一个面向真实场景的 Agent Harness

cloud-agent for OpenBSD 🕵️‍♀️

The Agent-native TypeScript stack

Computer-Use Agents as Judges for Generative UI

A proof of concept for RBAC on nginx with Open Policy Agent

Call Open Policy Agent (OPA) policies in WASM (Web Assembly) from .NET Core

SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents (UIST 2021)

Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)

🛳 Continuous deployment agent

Origami prototype for SpyBook - a fictitious social network for covert agents. Was a demo I gave as part of a CocoaHeads presentation.

This repository is an Reinforcement Learning Platform for learning agents to control cyber-physical Power Distribution Systems resiliently. The cyber environment in based on SimPy Discrete Event Simulator, while the distribution system is backened by Open-DSS.

OpenCode plugin that prevents agents/tools from reading or editing sensitive .env* files, while still allowing safe inspection via EnvSitter.

Decorator to retry calling a function upon error