Quick Start
Get a multi-agent system running in under two minutes. Three steps: initialize, configure your API key, and start.
Step 1 — Initialize a project
Run the init wizard to scaffold a new Hybrix project. It creates a config file, sets up a default agent, and generates a hybrid mascot for you.
bash
mkdir my-agents && cd my-agents
hybrix initThe wizard will ask you to pick an LLM provider (Anthropic, OpenAI, Google, or local), a role for your first agent, and two animals for its mascot. All choices can be changed later.
Step 2 — Add your API key
Create a .env file in your project root with your provider key:
env
# Pick the one matching your chosen provider
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
GOOGLE_AI_KEY=AI...Using Ollama for local models? No API key needed. Just make sure Ollama is running on port 11434 and you have at least one model pulled.
Step 3 — Start the gateway
Boot the Hybrix gateway. This starts the agent runtime, opens the web dashboard, and connects any configured channels.
bash
hybrix startOpen http://localhost:3000 in your browser to see the dashboard. Your agent is live and ready to chat.