Getting Started

Your first 10 minutes with Hoziron. By the end of this section, you'll have a running instance with an agent responding to messages.

What you'll need

  • A machine with 2+ CPU cores and 2 GB RAM (Linux, macOS, or Windows WSL2)
  • One of: a provider API key (Anthropic, OpenAI, Groq) or a local Ollama instance
  • Docker (optional, for container deployment)

Choose your install method

MethodBest forTime to first agent
Binary installLocal dev, bare metal servers~3 minutes
DockerContainer environments, quick eval~2 minutes
KubernetesProduction clusters~10 minutes

What happens during setup

  1. Install — Get the Hoziron binaries or container image
  2. Initialize — Creates your config directory with config.toml, .env, and data/
  3. Configure a provider — Point Hoziron at an LLM (cloud or local)
  4. Start — Launch the API server (hoziron-api)
  5. Create an agent — Spawn from a template and start chatting

Quick reference

CommandWhat it does
hoziron initInitialize config directory
hoziron statusShow platform status
hoziron healthQuick health check
hoziron doctorRun diagnostics (with --repair to auto-fix)
hoziron chatInteractive chat with default agent
hoziron agent listList all agents

Environment variables

VariablePurposeDefault
HOZIRON_HOMEConfig/data directory~/.hoziron
HOZIRON_LISTENDaemon listen address127.0.0.1:4200
HOZIRON_LOGLog level filterinfo
HOZIRON_LOG_FORMATLog format (text or json)text

Ready? Pick your install method and let's go.


Related: