Open SourcePowered by Matrix

Open Source Multi-Agent OS

Let multiple AI Agents collaborate in Matrix rooms, fully visible to humans, with real-time intervention capability. Manager Agent coordinates multiple Worker Agents to complete complex tasks.

Fast-track your OPOC (One Person One Company) and enterprise digital workforce.

Quick Start View on GitHub

Quick Start

One command to install. The script asks for your LLM API key, then sets everything up.

terminal

macOS / Linux

# Quick install (interactive)
$ bash <(curl -sSL https://hiclaw.domeclaw.com/dome-install.sh)

When it's done:

=== HiClaw Manager Started! ===

Open: http://127.0.0.1:18088
Login: admin / [generated password]

Tell the Manager: "Create a Worker named alice for frontend dev"

Why HiClaw?

Featuring enterprise-grade security and designed specifically for multi-agent collaboration, enabling AI agent teams to work together as efficiently as human teams

Enterprise Security

Workers never hold real API keys or GitHub PATs. They only carry a consumer token (like a badge). Even a compromised Worker can't leak your credentials.

Multi-Agent Collaboration

Manager Agent intelligently decomposes tasks and coordinates multiple Worker Agents for parallel execution, significantly improving complex task handling.

Matrix Protocol

Built on the open Matrix IM protocol, all Agent communications are transparent and auditable, with native support for distributed deployment and federation.

Human Supervision

Humans can enter any Matrix room at any time to observe Agent conversations, intervene or correct Agent behavior in real-time, ensuring safety and control.

Manager-Worker Architecture

Clear two-tier Manager-Worker architecture with distinct responsibilities, easy to extend with custom Worker Agents for different scenarios.

Fully Open Source

Completely open source, community-driven development, no vendor lock-in, supports local private deployment with full data sovereignty.

Prerequisites

Docker Desktop (macOS) or Docker Engine (Linux). That's all.

Docker Desktop (macOS)

Recommended for macOS users. Download from docker.com

Docker Engine (Linux)

Or Podman Desktop as an alternative

Minimum Requirements

The Docker VM needs at least 2 CPU cores and 4 GB RAM. In Docker Desktop, go to Settings → Resources to adjust.