Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getnen.ai/llms.txt

Use this file to discover all available pages before exploring further.

Prerequisites

  • A Nen API key — get one from the Dashboard

1. Install the Nen CLI

curl -fsSL https://releases.getnen.ai/install.sh | bash
Restart your shell (or run source ~/.zshrc / source ~/.bashrc), then verify:
nen --help

2. Run the Interactive Quickstart

nen quickstart
On first run it will prompt for your Nen API key, validate it, and save it automatically. Then choose a guide:
GuideWhat it does
1. Your first desktopProvisions a desktop, takes a live screenshot, tears it down — no code required
2. Manage desktopsWalks through every nen desktop command against a real desktop
3. Run an AI agentRuns a full Claude agent loop entirely in your terminal — no Python, no installation
4. Build your own agentScaffolds a ready-to-run agent project, pre-fills your API keys, and optionally runs it immediately
Guide 3 is the fastest way to see autonomous desktop control without touching code. Guide 4 leaves you with a working codebase you can modify and ship.

Manual Setup

If you prefer explicit control over each step, you can set up manually. Requires Python 3.12+.
1

Scaffold an agent project

nen example create anthropic-computer-use
cd nen-anthropic-cua
2

Install dependencies and configure

uv sync
cp .env.example .env
Edit .env and fill in your API keys:
.env
NEN_API_KEY=sk_nen_...
ANTHROPIC_API_KEY=sk-ant-...
Use OPENAI_API_KEY instead of ANTHROPIC_API_KEY if you scaffolded the OpenAI template.
3

Run the agent

The agent creates a desktop automatically, runs the task, and cleans up:
uv run python agent.py --task "Open Firefox and navigate to google.com"
Use --desktop-id dsk_abc123def456 to target an existing desktop, --keep to skip auto-cleanup, or --max-steps to control the loop length.

Next Steps

CLI Reference

Full CLI command reference

Supported Tools

All tools and supported models (Claude, GPT, and more)

Full Examples

Complete, production-ready agent loop examples

Cloud Desktops

Cloud desktop provisioning, lifecycle, and the tools API