Skip to content
MAESTRO

Quick Start

Get from a fresh checkout to a running agent in about five minutes.

Prerequisites

Section titled “Prerequisites”
  • Python 3.12+
  • uv (project + environment manager)
  • An OpenAI-compatible API key (e.g. OpenRouter)

1. Install

Section titled “1. Install”
Terminal window
uv sync

2. Configure

Section titled “2. Configure”

care init walks the minimum MAGE credentials (base URL, API key, model) and writes a ./.env so a fresh checkout can boot:

Terminal window
uv run care init

For CI / scripted setup, do it non-interactively:

Terminal window
uv run care init --non-interactive \
  --api-key sk-... \
  --base-url https://openrouter.ai/api/v1 \
  --model qwen/qwen3-coder

3. Launch the TUI

Section titled “3. Launch the TUI”
Terminal window
uv run care

MAESTRO CARE opens directly into the chat surface — a Claude-Code-style transcript with a prompt at the bottom and a mode toggle above it.

4. Generate your first agent

Section titled “4. Generate your first agent”

Type a task in natural language and press Enter:

Summarise the key risks in this quarterly report and rank them by severity.

MAGE generates a chain, MAESTRO runs it on the spot, and the answer prints inline. First-time users see a one-line offer to type /tour for a 5-step walkthrough.

Next steps

Section titled “Next steps”