Get Started with Auto Learning Agents

Install in Four Steps

Auto Learning Agents ships as a single Docker image with everything bundled, the Elixir runtime, the Python services, the local database, and the full tool layer. You go from nothing to a running platform with a handful of commands.

1. Install Docker

Install Docker and Docker Compose for your operating system if you do not already have them. Everything the platform needs runs inside the container, so Docker is the only requirement on your machine.

2. Clone the Repository

Pull the source from GitHub and move into the project directory.

git clone https://github.com/AIAppsAPI/auto-learning-agents
cd auto-learning-agents

3. Add Your API Keys

Copy the example environment file and add keys for the models you want to use, such as Claude, OpenAI, or Gemini. You can mix models freely, and you can run fully local with Ollama and no external keys at all.

cp .env.example .env
# open .env and add your API keys

4. Start the Platform

Bring everything up with one command. The first run prepares your local database and starts the full supervision tree of agent nodes.

docker compose up

Once it is running, open http://localhost in your browser to reach the dashboard. Your agents are live and ready for their first task.

What You Need

The requirements are deliberately light. You need Docker on your machine, and at least one way for the agents to think, either an API key from a provider like Anthropic, OpenAI, or Google, or a local model served through Ollama. Storage and search run on a single bundled database, so there is nothing external to set up and no cloud account to create. You own the whole stack.

Documentation and Next Steps

The repository ships with a README and a docker-compose setup that walk through configuration, model selection, and the memory backend in detail. To understand the system behind the platform, the guides cover how agents work, the frameworks involved, and how to run them yourself, all linked from the home page.