Documentation

Installation

Installing from a desktop environment? Start with Agent Zero Launcher. Already in a terminal? Use A0 Install.

Agent Zero installation walkthrough Play video

Install Agent Zero with Launcher

On a desktop, these three steps are all you need. Launcher guides you through creating and opening Agent Zero.

Step 1

Download Launcher

Choose the download for your computer. Apple Silicon means an M-series Mac; most other desktop and laptop computers use x64.

Architecture macOS Linux Windows
x64 Mac Intel Linux x64 Windows x64
ARM64 Mac Apple Silicon Linux ARM64 Windows ARM64

Need release notes or updater metadata? See the A0 Launcher v1.6 release.

Using a terminal or server instead?

Use A0 Install from a terminal, SSH session, or server shell. If Docker is already running, choose the Docker tab to start Agent Zero directly.

# A0 Install for macOS or Linux.
$ curl -fsSL https://bash.agent-zero.ai | bash
# A0 Install for Windows: run in PowerShell.
> irm https://ps.agent-zero.ai | iex
# Direct Docker: use when Docker is already installed and running.
$ docker run -p 80:80 -v a0_usr:/a0/usr agent0ai/agent-zero

Headless or scripted setup: Quick Start mode creates one Instance and exits without opening installer menus. 

curl -fsSL https://bash.agent-zero.ai | bash -s -- --quick-start --name agent-zero --port 5080
& ([scriptblock]::Create((irm https://ps.agent-zero.ai))) -QuickStart -Name agent-zero -Port 5080

Add --skip-runtime-setup or -SkipRuntimeSetup when Docker must already be working and the installer should not try to set up a runtime.

Step 2

Create your first Instance

Open Launcher and follow any setup prompt. When it is ready, choose Download Agent Zero or Run Agent Zero, keep latest selected, then click Create.

Launcher Create local Instance dialog with latest selected
The default version is ready to use. Naming, login, and Advanced settings are optional.
Step 3

Open Agent Zero

Wait for the Instance to show Running, then click Open UI. Complete the short onboarding flow in the Web UI and start chatting.

Launcher Instances view with Open UI buttons
Open Agent Zero from its running Instance card.

Need remote Instances, backups, or Host access? The Launcher guide covers those when you need them.

Add host control with A0 CLI

Agent Zero normally runs separately from your computer. If you want it to work on files on your own computer, run commands in your host terminal, or use your host browser profile, install A0 CLI on the host machine before you configure models.

Optional

Install A0 CLI on this computer

Run the command for your platform in your host terminal or PowerShell, not inside the Agent Zero container. After it connects, Agent Zero can request access to local files, terminal execution, and Bring Your Own Browser workflows.

# Installs A0 CLI on your host computer.
$ curl -LsSf https://cli.agent-zero.ai/install.sh | sh
# Installs A0 CLI from Windows PowerShell.
> irm https://cli.agent-zero.ai/install.ps1 | iex

For the full setup path, open the A0 CLI Connector guide.

Configure models and providers

Once the Web UI opens, finish onboarding by connecting at least one model provider. Use the guided onboarding prompt if it appears, or open the same flow again from Settings later. The goal is simple: choose Cloud, AI account, or Local access, then pick your main and utility models.

Agent Zero welcome screen with account setup shortcuts
Step 3

Complete the onboarding wizard

  1. Choose Cloud for OpenRouter, our proxy API, Anthropic, OpenAI, Google, Venice, or another hosted provider.
  2. Choose AI account for Codex/ChatGPT, GitHub Copilot, Google Cloud Gemini, or xAI Grok sign-in.
  3. Choose Local for Ollama, LM Studio, or another model server running on your machine.
  4. Pick the provider, paste the API key if that provider requires one, then choose the main model.
  5. Choose the utility provider and model for quick internal tasks such as summaries, naming, and memory.
  6. Click Finish setup, then start chatting.

Good default: use a capable main model for chat and a small, fast utility model for internal work.

Onboarding utility model step with provider and model choices

For the full screenshot walkthrough, open the First-Run Onboarding guide.

Run local models

Cloud providers are the fastest way to get started. If you want privacy-first or offline operation, run a local model server on the host machine and point Agent Zero at it from the same model configuration flow you used above.

Ollama

Great default for local inference. It is simple to install and works well for most self-hosted setups.

LM Studio

Good if you prefer a desktop app workflow and want to use its OpenAI-compatible local server.

Ollama quick path

  • Windows/macOS: install Ollama from ollama.com
  • Linux: run curl -fsSL https://ollama.com/install.sh | sh
# Start with a practical general model
ollama pull llama3.2

# Optional smaller variant
ollama pull llama3.2:1b
  1. Open the model configuration screen in Agent Zero.
  2. Select Ollama as the provider for the model slot you want to change.
  3. Use http://host.docker.internal:11434 as the base URL.
  4. Enter the local model name, then save.

Note: do not use localhost or 127.0.0.1 in Agent Zero for a model server running on the host. From inside Docker, those addresses point back to the Agent Zero container. Use host.docker.internal when available, or the Docker host gateway address such as 172.17.0.1 on the default Linux bridge.

For LM Studio, enable its local API server and use the same model configuration flow. If LM Studio shows a localhost URL, replace the host part with the Docker-reachable host address before saving it in Agent Zero.

If a local server only listens on 127.0.0.1 on the host, Docker still cannot reach it. Configure the server to listen on a Docker-reachable address, such as 0.0.0.0, and keep the port limited to trusted clients.

Local model configuration in Agent Zero

Understand the model roles

Chat model

The main reasoning model used for conversation, planning, and most higher-value work.

Utility model

Helper model for faster supporting tasks. You can keep it on the same provider at first.

Embedding model

Powers memory and knowledge indexing. Changing it later can trigger reindexing work.

Data persistence and backups

Your running container can be replaced or recreated over time, so think about data before you upgrade or experiment. The safest default is still the built-in backup flow.

Option 1: Backup and Restore

  1. Open Settings -> Backup & Restore.
  2. Create a backup and keep the file somewhere safe.
  3. Restore that backup into a fresh installation or container when needed.

Option 2: Volume mapping

Use a Docker volume or bind mount only when you want a host-managed directory. Map a folder on your machine to /a0/usr inside the container. 

docker run -d -p 50080:80 -v /path/to/local/folder:/a0/usr --name agent-zero agent0ai/agent-zero
  • Do not map the entire /a0 directory when upgrading.
  • Prefer one clean mapping to /a0/usr.
  • Create a backup before major updates even if you already use volumes.

Network access and sharing

You can keep Agent Zero local, expose it to devices on your network, or share it over the internet once authentication is enabled.

Local network

  1. Find your computer IP address with ipconfig on Windows or ifconfig / ip addr on macOS and Linux.
  2. From another device on the same network, open http://your-ip:your-port.
  3. Example: http://192.168.1.100:50080.

Internet access

  1. Enable authentication first.
  2. Open the tunnel or sharing section in Settings.
  3. Create a tunnel and use the generated URL or QR code.

For more detail, the separate Sharing guide expands on network access and safe collaboration.

Security reminder: never expose the instance to the internet without Web UI authentication enabled.

Need help?

If installation or onboarding does not behave as expected, the community channels below are the fastest place to compare notes and get unstuck.

Community support

Useful next docs