Auto Learning Agents

Auto Learning Agents is a free, open-source platform that lets you run your own AI agent system. You install it on your own hardware using Docker, add API keys for the models you want, and start it with a single command. In minutes, you have a dashboard where agents are ready to take on tasks. Everything runs locally — no cloud account, no external databases, no vendor lock-in.

The platform bundles the Elixir runtime, Python services, a local database, and a full tool layer into one Docker image. You choose which AI models to use: Anthropic's Claude, OpenAI's GPT, Google's Gemini, or fully local models through Ollama. You can mix them freely in the same workflow. The first run prepares the database and starts a supervision tree of agent nodes. Setup is deliberately simple — Docker is the only requirement on your machine.

This tool is built for developers and teams who want full control over their AI infrastructure. You own the stack, the data, and the configuration. Use cases include running autonomous agents for research, building custom automation pipelines, or experimenting with agent frameworks without paying per-token fees to a cloud provider. The repository ships with detailed documentation and a docker-compose setup to guide you through model selection and memory backend configuration.