← Discover
GitHub · TencentCloud/Octop↑ +367 today

Multi-user AI on your own server

Octop, developed by TencentCloud, is a multi-user and multi-agent AI assistant that you can host on your own server. This Python-based system allows different users to interact with multiple AI agents simultaneously.

Updates

  • November 6, 2026: Stars 11,661 → 11,717, latest release v1.0.3b4 (November 6, 2026).
  • November 5, 2026: Stars 11,462 → 11,661, latest release v1.0.3b3 (November 4, 2026).
  • November 2, 2026: Stars 10,946 → 11,462, latest release v1.0.3b2 (November 2, 2026).
  • October 25, 2026: Stars 10,066 → 10,946, latest release v1.0.3b1 (October 25, 2026).

What you get

  • Manage multiple AI agents simultaneously
  • Store your data securely on your local disk
  • Access via web interface, messaging apps, and terminal

Installation

installation command
curl -fsSL https://finnie-1258344699.cos.ap-guangzhou.myqcloud.com/octop/install.sh | bash

Running it

First run
octop init

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to set up a multi-user and multi-agent work environment on the Octop platform. Define agents with different areas of expertise for my personal assistant, family members, or small team members, and ensure these agents work securely on my local data and collaborate with me via the web interface or messaging channels. Configure the MBTI personality traits of the agents, enable them to generate responses from my private documents using RAG (Retrieval-Augmented Generation), and automate my tasks.

Repository: https://github.com/TencentCloud/Octop. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forSuitable for individuals and small teams who prioritize privacy on their own server and want to manage numerous AI agents from a single hub.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-18: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.