Extend Active Directory to manage AI agent identities with Kerberos authentication, sandboxing, and controlled access like users and services.
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.
You will need a Windows computer with:
No special programming tools are needed. This guide shows you how to get agent-directory running on your PC.
Go to the agent-directory releases page to get the software:
This page shows the latest versions available. You will find the installation files here.
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.
After downloading, open the folder where the file saved.
This will create a new folder with the software files.
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."
Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents
Ultimate Multi-Agent OS for Autonomous AI NPCs 2026
PrivateAgent is an open-source Android automation agent built with Flutter. It utilizes the DeepSeek API and native Android Accessibility Services to interpret screen layouts and execute multi-step tasks across any installed application via natural language commands.
把一队分工 Agent 织成一条写小说的流水线,做成桌面客户端;写作指纹让它越写越像你(BYO DeepSeek key,纯本地)。
Workflows from the Neura Market marketplace related to this DeepSeek resource