Artificial

Artificial

An open source AI agent harness for orchestrating multiple AI workers from a single dashboard. Built in Go.

Artificial lets you spawn, manage, and coordinate AI agents (Claude Code, OpenAI Codex, ACP-compatible models, local LLMs) as a team. Agents get personas, skills, communication channels, and a shared task board. You manage them from a real-time web dashboard or the REST API.

What it does

- Multi-agent orchestration — run multiple AI agents in parallel, each with their own role and persona
- Real-time dashboard — chat with agents, manage tasks on a kanban board, monitor activity
- Channel-based communication — agents can message each other and receive notifications mid-task
- Multiple backends — supports Claude Code, OpenAI Codex, ACP (Agent Communication Protocol), and local models via OpenAI-compatible APIs
- MCP integration — each worker exposes tools to its agent via Model Context Protocol
- Session persistence — stop and resume agent sessions without losing context

Architecture

Quick start

Prerequisites

- Go 1.25+
- Claude Code CLI, OpenAI Codex CLI, or an ACP-compatible agent server

First steps

1. Set up company knowledge — create a folder with a README describing your project, conventions, and priorities (see Company knowledge). Set the path in dashboard Settings.
2. Create a CEO — add an employee with the "CEO" role from the dashboard. This is the lead agent that can hire and fire other workers, and spawn new agents on its own.
3. Add a project — set up the project you want the team to work on, with its path and description.
4. Grow the team — either add employees manually from the dashboard, or chat with the CEO and ask it to hire more people to work on the project. The CEO can spawn and manage workers autonomously.

Project…