Start a project
The recipe below installs the engine, creates a project, and starts it. Select your llm provider, or select no llm to set up a project without one. Every recipe adds console, the browser ui for your running system; a provider also adds harness which enables both agentic development and use of agents within your iii system. You can add a provider worker later at any time.select your llm provider
# No llm needed. Add a provider worker whenever you want agents.
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export OPENAI_API_KEY=yourkey
# Set up your llm provider
# No api key. This provider uses your chatgpt subscription.
# Sign in with the codex cli first, so ~/.codex/auth.json exists:
$codex login
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export ANTHROPIC_API_KEY=yourkey
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export DEEPSEEK_API_KEY=yourkey
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export MOONSHOT_API_KEY=yourkey
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export OPENROUTER_API_KEY=yourkey
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export XAI_API_KEY=yourkey
# Set up your llm provider
# The leading space keeps the export out of bash/zsh history (if you have history control enabled)
$ export ZAI_API_KEY=yourkey
# Set up your llm provider
# No api key. Your github copilot subscription grants the models.
# Set up your llm provider
# Runs against your own llama-server, http://127.0.0.1:8080 by default.
# A key is only needed when llama-server runs with —api-key:
$ export LLAMACPP_API_KEY=yourkey
# Install iii & setup your project
$curl -fsSL https://install.iii.dev/iii/main/install.sh | sh
$iii project init iii-app && cd iii-app
$iii
# New terminal, same folder
$iii worker add console
$iii worker add harness console provider-openai
$iii worker add harness console provider-openai-codex
$iii worker add harness console provider-anthropic
$iii worker add harness console provider-deepseek
$iii worker add harness console provider-kimi
$iii worker add harness console provider-openrouter
$iii worker add harness console provider-xai
$iii worker add harness console provider-zai
$iii worker add harness console provider-github-copilot
# Sign in once the provider worker is up:
$iii trigger provider::github-copilot::login::start
$iii worker add harness console provider-llamacpp
# Open your browser to http://localhost:3113
Next Steps
Quickstart
Follow the Quickstart and explore a live iii application.
Use iii
Learn how to use iii in production.