Skip to main content

​
System Requirements

AgentSystems requires:
  • Python 3.11 or higher
  • Docker (Docker Desktop on macOS, Docker Engine on Linux)
  • Operating System: macOS or Ubuntu Linux
1

Install AgentSystems

Run the installation script:
curl -fsSL https://github.com/agentsystems/agentsystems/releases/latest/download/install.sh | sh
2

Initialize Deployment

Create and enter your deployment directory:
agentsystems init my-deployment
cd my-deployment
The init command prompts for:
  • Langfuse credentials for observability
  • Admin credentials for the UI
3

Start the Platform

Launch all platform services:
agentsystems up
This starts:
4

Pull a Local Model

Download a small model for local testing:
docker exec agentsystems-ollama-1 ollama pull gemma3:1b
This downloads a local AI model without needing API keys.
5

Open the UI

Open http://localhost:3001 in your browser to execute your first local agent.

​
Stop the Platform

When you’re done: 
agentsystems down
⌘I