Skip to main content

​
Step 1: Install Lukan Agent

curl -fsSL https://get.lukan.ai/install.sh | bash
Supported platforms:
  • Linux (glibc): x86_64, arm64
  • macOS: x86_64, arm64 (Apple Silicon)
Alpine/musl and Windows are not supported. Use WSL on Windows.

​
Step 2: Configure

lukan setup
This interactive wizard helps you:
  1. Select a model provider (Nebius, Anthropic, Fireworks, GitHub Copilot, OpenAI Codex, z.ai, Ollama Cloud, OpenAI Compatible, Lukan Cloud)
  2. Enter your API key
  3. Set your timezone

​
Step 3: Start the assistant

lukan
This opens the interactive CLI chat.

​
Step 4: Describe the goal

Use natural language to request concrete outcomes: 
Open the project, find all TODO comments, and create a short action list.
Lukan then plans, connects tools, executes actions, and validates the result.

​
Optional: Initialize a project

cd your-project
lukan init
This creates a .lukan/ directory with:
  • config.json - Project-specific permissions
  • memories/MEMORY.md - Project context that persists across sessions

​
What to do next

Capabilities

Understand how Lukan plans and executes complex workflows.

CLI Reference

Learn the core commands for daily usage.

Permissions

Configure what Lukan can and cannot do in your project.

Providers

Configure model providers and API keys.