Golem: Embodied Agent Protocol

Control virtual characters via WebSocket-based Golem Protocol in Unity.

5|4|Updated Jan 16, 2026
One-click install
npx skills add https://github.com/TreasureProject/Golem --skill golem-embodied-agent-protocol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Golem: Embodied Agent Protocol
Source: https://github.com/TreasureProject/Golem/tree/main/openclawSkill
Command: npx skills add https://github.com/TreasureProject/Golem --skill golem-embodied-agent-protocol

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables AI agents to control characters in virtual environments by providing a standardized communication protocol, allowing for dynamic interaction and learning within simulated worlds.

Core Features & Use Cases

  • AI-to-Character Communication: Facilitates real-time interaction between AI models and virtual avatars via WebSockets.
  • Dynamic Action Execution: Supports movement, voice, animation, and object interaction commands.
  • Learning and Adaptation: Enables AI agents to learn from environmental feedback and adapt their behavior.
  • Use Case: An AI agent can be tasked with navigating a virtual city, interacting with objects like doors and computers, and responding to other characters, all through this protocol.

Quick Start

Connect to the Golem WebSocket endpoint at ws://localhost:5173/agents/chat/external:character.

Frequently Asked Questions about Golem: Embodied Agent Protocol

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I control virtual characters with AI in Unity?

You can control virtual characters with AI by connecting your AI agents to a WebSocket endpoint, which facilitates real-time interaction, movement, and voice commands within game engines like Unity.

What is the Golem Protocol for embodied AI agents?

The Golem Protocol is a standardized WebSocket-based communication framework that enables embodied AI agents to control virtual characters and execute dynamic actions within simulated game environments.

How do AI agents learn from environmental feedback in virtual environments?

AI agents learn from environmental feedback through perception-action feedback loops, allowing them to adapt their behavior based on dynamic interactions with objects and other characters.

Can I use WebSockets to facilitate AI-to-character communication for game development?

Yes, WebSockets facilitate real-time AI-to-character communication by connecting AI models to virtual avatars, supporting dynamic action execution like movement, voice, and animation.

Does the Golem Protocol support object interaction and custom scripting in game engines?

Yes, the Golem Protocol supports object interaction and custom scripting within game engines, enabling AI agents to navigate virtual spaces and interact with items like doors and computers.

What actions can an embodied AI agent perform using WebSocket-based character control?

An embodied AI agent can perform movement, voice, animation, object interaction, and custom scripting actions by connecting to the standardized WebSocket-based Golem Protocol.