AI News HubLIVE
In-site rewrite6 min read

Agent Zero – A full Docker Linux system for your AI agent

Agent Zero is an open, dynamic, organic agentic framework. One Docker container ships a full Linux system with a desktop and a plugin hub that the agent can extend using Skills. It includes a real Linux desktop, a native browser with DOM annotations, document coworking, LibreOffice integration, 100+ community plugins, multi-agent cooperation, and host machine extension via the A0 CLI Connector.

SourceHacker News AIAuthor: modinfo

Uh oh!

There was an error while loading. Please reload this page.

Uh oh!

There was an error while loading. Please reload this page.

Notifications You must be signed in to change notification settings

Fork 3.7k

Star 18.2k

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

2,365 Commits

2,365 Commits

.github

.github

.vscode

.vscode

agents

agents

api

api

conf

conf

docker

docker

docs

docs

extensions

extensions

helpers

helpers

knowledge

knowledge

lib

lib

logs

logs

plugins

plugins

prompts

prompts

scripts

scripts

skills

skills

tests

tests

tmp

tmp

tools

tools

usr

usr

webui

webui

.dockerignore

.dockerignore

.gitattributes

.gitattributes

.gitignore

.gitignore

AGENTS.md

AGENTS.md

CONTRIBUTING.md

CONTRIBUTING.md

DockerfileLocal

DockerfileLocal

LICENSE

LICENSE

README.md

README.md

agent.py

agent.py

initialize.py

initialize.py

jsconfig.json

jsconfig.json

models.py

models.py

preload.py

preload.py

prepare.py

prepare.py

requirements.dev.txt

requirements.dev.txt

requirements.txt

requirements.txt

run_tunnel.py

run_tunnel.py

run_ui.py

run_ui.py

update_reqs.py

update_reqs.py

Repository files navigation

A full Linux system for your AI agent.

Agent Zero is an open, dynamic, organic agentic framework. One Docker container ships a full Linux system with a desktop and a plugin hub that the agent can extend using Skills.

Install | Launcher | What's Different | A0 CLI | Docs

Ask ChatGPT | Ask Claude

How To Install

Choose the install path that matches your machine.

Path Best for What it does

A0 Launcher Desktop users who want the guided path Downloads Agent Zero, creates and manages local Instances, and helps set up the container runtime when needed.

A0 Install Terminals, SSH sessions, servers, and scripted setup Installs Agent Zero from the command line, reuses an existing Docker-compatible runtime first, and can run headlessly.

Docker Machines that already have Docker ready Runs the Agent Zero container directly.

A0 Launcher

The desktop A0 Launcher is the recommended way to install Agent Zero on a personal machine. Download the Launcher, open it, and let it check your local runtime. If Docker is missing or stopped, the Launcher offers a setup path before it downloads Agent Zero. If you already host Agent Zero elsewhere, add it as a remote Instance and use the Launcher without local Docker setup.

Downloads

Architecture macOS Linux Windows

x86 Mac Intel Linux x86 Windows x86

ARM64 Mac Apple Silicon Linux ARM64 Windows ARM64

See the A0 Launcher v0.9 release for release notes and updater metadata. See the Launcher guide for the first-run walkthrough.

A0 Install

Use A0 Install when you want the terminal path: SSH sessions, servers, recovery shells, or a scriptable setup. It creates Dockerized Agent Zero instances, mounts each instance's data into /a0/usr inside the container, and uses a reuse-before-setup policy: it tries your current Docker CLI configuration, DOCKER_HOST, Docker contexts, and known local Docker-compatible endpoints before setting up a runtime.

macOS / Linux

curl -fsSL https://bash.agent-zero.ai | bash

Windows PowerShell

irm https://ps.agent-zero.ai | iex

Headless / scripted

For servers and automation, run the installer in Quick Start mode so it creates one instance and exits without opening 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

Use --skip-runtime-setup / -SkipRuntimeSetup when Docker must already be working and the installer should not try to set up a runtime. See the A0 Install repository for all installer flags.

Docker already installed? Run this directly

docker run -p 80:80 -v a0_usr:/a0/usr agent0ai/agent-zero

Open the Web UI, configure your LLM provider, and start with a concrete task. For the full setup and onboarding experience, see the Installation guide.

What Makes Agent Zero Different

A Real Linux Desktop in the Canvas

Agent Zero opens its own Linux desktop inside the right-side Canvas. Not a remote VM, not a shared clipboard, but a real XFCE desktop session running in the container.

That means the agent can drive real desktop software: open Blender to model a 3D object, jump into a terminal window, manage files visually, run a GUI tool that has no API.

You watch every action, and you can intervene at any moment because your mouse and keyboard share the same desktop.

See the Desktop guide for the walkthrough, prompt examples, and how Desktop differs from Browser.

Native Browser With DOM Annotations

Agent Zero ships a built-in Browser with an optional live surface in the Canvas. The agent can open pages, read them, click, type, upload files, and take screenshots - the usual. The unusual part is Annotate mode.

Annotate mode turns any webpage into an interactive directive surface. Click an element to:

Change it - "make this button blue and round the corners" runs as a JS instruction the agent applies and verifies.

Inspect it - pull the DOM, the styles, the parent chain, the framework hints into the conversation.

Lift it - see a card, hero, or component on someone else's site that you like? Capture it and have the agent re-implement it in your own project's stack.

Comment it - leave actionable notes pinned to elements during a UI review; the agent reads the comments and ships the fixes.

The Docker browser is the default live Browser surface. Browser history keeps screenshots of important steps, so older chats can still show what the agent saw. The Browser also supports Chrome extensions inside the Docker browser, and Bring Your Own Browser through the A0 CLI Connector lets the agent drive Chrome/Edge/Chromium on your own machine.

See the Browser guide for screenshots, settings, host-browser setup, and troubleshooting.

Cowork on Documents

Markdown Editor With Live Cowork

The Canvas includes a rich Markdown editor designed for genuine cowork. Ask the agent to "write a plan to do X in a TODO.md in the open doc" and you'll see the file appear in the editor, character by character, while you keep typing in another section.

It's not a preview pane. It's a real editor with toolbar, formatting buttons, tables, and an editable source view - built so that the agent's edits and yours are equal first-class operations on the same document.

Use it for plans, TODOs, meeting notes, RFCs, project handoffs, or any artifact where the deliverable should live as text rather than be trapped inside chat scrollback.

LibreOffice Integration

LibreOffice Writer, Calc, and Impress are wired up so you can type by hand while Agent Zero creates, updates, saves, and verifies the same files in real time.

ODT, ODS, and ODP binary formats are first-class citizens in the Agent Zero Desktop environment to align with the Open Document Format (ODF).

Use the Desktop toolbar to create and edit Writer, Spreadsheet, and Presentation LibreOffice files.

Plugin Hub - 100+ Community Plugins

Agent Zero is built for extension, not just configuration. The built-in Plugin Hub browses a growing catalog of community plugins - currently more than 100, covering:

Development frameworks like the BMAD Method (full software development lifecycle with 20 specialist agents) and Agent Skills.

Memory systems - alternative memory backends, intelligent consolidation strategies, vector recall plugins.

Tools and integrations - embedded terminals, custom browsers, deployment helpers, API clients.

UI extensions - chat rename controls, sidebar tweaks, theme packs, custom Canvas panels.

Workflow plugins - schedulers, multi-agent orchestration, project automations.

Install with a click from the Web UI, or publish your own to the index repository. Combined with custom prompts in prompts/, custom tools in tools/, MCP servers, A2A connectors, and project-scoped configuration, Agent Zero gives you a real surface area to shape the agent into whatever you need.

See the Skills guide, the Create a Small Plugin tutorial, and the MCP setup guide.

Use Your OpenAI Codex Plan

Agent Zero connects to your OpenAI Codex plan through the new OAuth flow. Sign in with your account, pick the Codex-backed provider, and let Agent Zero use the plan you already have. Click "Connect", enter the device code in the OpenAI page, choose your model, and you're set.

This is the first step toward account-backed LLM plans in Agent Zero. More integrations are coming, including Gemini CLI and Claude Code through extra-usage.

A0 CLI Connector: Extend Onto Your Host Machine

The A0 CLI Connector is not a separate CLI agent. It connects to a running Agent Zero instance and gives that instance a terminal-native bridge to your host machine - so the same agent (with all its memory, projects, and skills) can also work on real files outside the Docker container.

Install the connector on the machine you want Agent Zero to work on, not inside the Agent Zero container.

macOS / Linux

curl -LsSf https://cli.agent-zero.ai/install.sh | sh

Windows PowerShell

irm https://cli.agent-zero.ai/install.ps1 | iex

Then run a0 to connect your terminal to an existing Agent Zero instance. It can usually discover a local instance automatically, or you can point it at a remote URL hosted somewhere else, such as a VPS or tunnel.

This is especially useful if you:

prefer CLI workflows;

want Agent Zero to work in an existing local repository;

are running Agent Zero on a remote server;

want Docker isolation for Agent Zero while still granting explicit, controlled access to host-side work.

For full setup, see the A0 CLI Connector guide (or the in-repo guide).

Projects, Skills, Agent Profiles, and Model Presets

Projects isolate workspaces, instructions, memory, secrets, knowledge, repositories, and model presets. Clone a public or private Git repo into a project and give the agent context that belongs to that work alone.

Skills can be loaded on demand by Agent Zero, or pinned from the chat input when you want a specific procedure to stay active.

Agent Profiles change the broader working style of the current chat.

Model Presets are named shortcuts for model setups, so you can quickly switch between fast, balanced, cheap, local, or high-power model choices.

Multi-Agent Cooperation

Every agent can create subordinate agents to break down work. The superior gives tasks and receives reports; subagents keep their own contexts focused and return their findings when done.

This makes Agent Zero useful for research, software engineering, data analysis, plugin development, and tasks where several specialized perspectives are better than one overloaded context.

Transparent and Extensible by Design

Almost nothing is hidden. Prompts live in prompts/, tools live in tools/ or plugins, and built-in behavior can be inspected, changed, replaced, or extended.

Agent Zero supports plugins, MCP, A2A, custom tools, custom prompts, project-scoped configuration, environment-based deployment settings, and a Web UI designed to keep the agent's work readable in real time.

Try These First

Annotate a design you like: "Open this template site in the Browser. I'll annotate the hero section - re-implement it in my project's React + Tailwind stack."

Cowork on a spreadsheet: "Create an editable ODS budget model with assumptions and monthly projections."

Drive a desktop app: "Use the Linux Desktop to open Blender and create a simple 3D logo for me."

Review a web UI: "Open my local app in the Browser. I will annotate the page with comments; then implement the requested U

[truncated for AI cost control]