Agent Zero

AI agents with a full Linux system at their fingertips.

Agent Zero is a dynamic, organic agentic framework for running AI agents that can create tools, write code, browse the web, cooperate with other agents, and keep learning from your goals and projects.

Introduction | Space Agent | Quick Start | LLM Plans | CLI Connector | Browser | Desktop | Features | Examples | Docs

Ask ChatGPT | Ask Claude

What Is Agent Zero

Agent Zero is not a predefined one-purpose agent.

It is a transparent, extensible framework where the agent can use the operating system as a tool: a real Linux environment, terminal, code execution, files, memory, browser automation, plugins, and tools it learns to create along the way.

The goal is simple: give an AI agent enough environment, memory, communication, and freedom to solve real tasks while keeping the work inspectable and steerable by you.

How To Install

macOS / Linux

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

Windows PowerShell

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

Docker Desktop already installed? Use this command directly

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

Then open the Web UI, configure your LLM provider, and start with a concrete task. For the full setup path, including updates and platform notes, see the Installation guide.

What Makes Agent Zero Different

Computer as a Tool

Agent Zero can use a Kali Linux system to accomplish your task. It can inspect files, run commands, write code, install and use tools, create scripts, search the web, and adapt its workflow as the task evolves.

The important idea is not a fixed list of buttons. The important idea is that the agent can build and use the right tool when the work demands it.

Canvas

Agent Zero is becoming more visual and shared. The right-side Canvas gives agents and humans working surfaces for browser sessions, documents, workspace history, and other plugin panels.

The Canvas makes agent work visible. You can watch it browse, inspect what changed, open files, cowork on deliverables, and intervene before a small mistake becomes a large one.

Linux Desktop and LibreOffice Cowork

The Desktop surface opens Agent Zero's own Linux desktop in the Canvas. It is useful when the work needs a real GUI: Linux desktop apps, a terminal window, visual file management, or LibreOffice running where you and the agent can both see it.

Create, open, and cowork with the AI on documents, spreadsheets, and presentation decks with the LibreOffice stack.

The Desktop toolbar can create Markdown, Writer, Spreadsheet, and Presentation files. LibreOffice Writer, Calc, and Impress run inside the Desktop, so you can type by hand while Agent Zero creates, updates, saves, and verifies the same files.

The document Canvas supports Markdown by default, with LibreOffice-native ODT, ODS, and ODP workflows when binary office artifacts are needed. Microsoft Office compatibility imports and exports remain available when explicitly requested.

Markdown, Writer, Spreadsheet, and Presentation files share a compact active-file header with save, rename, close, and creation controls in both Canvas and modal views.

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

Native Browser With Annotations and Extensions

Agent Zero includes 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 Docker browser is the default live Browser surface. With A0 CLI, Agent Zero can also use Bring Your Own Browser to work with Chrome, Edge, or Chromium on your own computer. Open the Browser surface when you want to watch the Docker browser, or ask Agent Zero to show it in the Canvas.

Browser history keeps screenshots of important steps, so older chats can still show what the agent saw.

For web and mobile development, Annotate mode lets you click page elements or regions and leave actionable comments for the agent targeted at the page itself. You can review a UI visually, mark what needs to change, and send those notes straight back into the conversation.

The Browser also supports Chrome extensions inside the Docker browser. See the Browser guide for screenshots, settings, host-browser setup, and troubleshooting.

Use Your OpenAI Codex Plan

Agent Zero can now connect 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 after checking the list, and you're all set.

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

A0 CLI Connector: Use Agent Zero on 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.

Agent Zero stays responsible for the reasoning loop, memory, projects, profiles, model choices, and tools. The CLI is how you intentionally let that Agent Zero instance work beyond the Docker container: on your host machine, in a terminal-first workflow, or against a server where you do not want a GUI at all.

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

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

Inside the shell, use Ctrl+P for the command palette, /chats to switch work, /models or /presets to adjust models, and /browser status to check Browser mode.

When you activate Read+Write access and the Remote Code Execution Tool in the CLI, Agent Zero can operate on the filesystem and shell of the machine where a0 is running. That means it can work on your real local project files, not only files inside the Docker sandbox.

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;
• need code execution on a headless machine without using the Web UI;
• want Docker isolation for Agent Zero while still granting explicit, controlled access to selected host-side work.

For full setup details, manual fallback installation, and remote-host tips, see the A0 CLI Connector 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 an isolated 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 users 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.

Also Included

• Fully Dockerized runtime with a clean Web UI.
• Real-time streamed output so you can interrupt, redirect, or refine the work as it happens.
• Speech-to-text and text-to-speech support through the built-in _kokoro_tts and _whisper_stt plugins, with browser-native speech synthesis as the fallback output path.
• Chat load/save, generated HTML logs, file browser, settings UI, and deployment-friendly A0_SET_ configuration.

Try These First

• Research with the Browser tool: "Use the Browser tool to compare three project management tools for a small AI team, and summarize the tradeoffs with source links."
• Cowork on a spreadsheet: "Create an editable ODS budget model with assumptions and monthly projections."
• Review a web UI: "Open my local app in the Browser. I will annotate the page with comments; then implement the requested UI fixes."
• Work inside a Git project: "Clone this repository into a new project, understand the layout, and propose the safest first improvement."
• Create a specialist: "Create an Agent Profile for financial analysis with cautious reasoning, clear assumptions, and spreadsheet-first deliverables."
• Recover a workspace: "Show me recent Time Travel snapshots and explain what changed before I revert anything."

Agent Zero and Space Agent

Agent Zero is the open framework and Linux-powered agent workbench.

Space Agent is our newer product direction for the agent-shaped workspace: a Space the agent can reshape from inside your browser, with live demos, a desktop app, and a path to running a real server for yourself or your team.

If you want the raw power and deep customizability of an agent with a full Linux system, start here with Agent Zero. If you want the polished Space experience for easier personal, team, desktop, or self-hosted use, explore Space Agent.

Time Travel (powered by Space Agent)

Time Travel gives Agent Zero-owned /a0/usr workspaces snapshot history, diff inspection, travel, and revert. It is designed for recoverable agent work: see what changed, compare files, inspect a past state, and roll back when needed. Try it in Space Agent as well (link above).

It is not a replacement for Git or backups. It is a practical safety layer for the workspace where agents are actively creating and editing files.

Real-World Use Cases

• Software engineering: inspect a codebase, make scoped edits, run tests, explain tradeoffs, and keep a recoverable history of file changes.
• Host-machine development: connect with a0, grant Read+Write and remote execution when needed, and let Agent Zero work in your real local repositories.
• Financial analysis and charting: collect data, correlate events, create spreadsheets, and generate editable charts.
• Office deliverables: cowork on documents, spreadsheets, and presentation decks instead of trapping the result in chat text.
• Web and mobile QA: browse an app, annotate UI issues, install browser extensions, and turn visual comments into actionable fixes.
• API integration: paste an API snippet, let the agent build a working example, and store the pattern for future use.
• Client/project isolation: keep memory, secrets, instructions, files, and model choices separated by project.
• Scheduled operations: run recurring checks and monitoring tasks with project-scoped context and credentials.

Safety Model

Agent Zero is powerful because it can use a real environment. Treat it with the same respect you would give a capable developer with shell access.

• Keep it running inside Docker or another isolated environment.
• Do not mount your entire home directory unless you understand the risk.
• Grant A0 CLI Read+Write access and remote code execution only for machines and workspaces you trust.
• Store credentials in project secrets or settings, not in prompts or public files.
• Review actions that touch accounts, money, production systems, or private data.
• Keep backups for important workspaces.
• Install browser extensions and third-party plugins only from sources you trust.

Documentation

Build With Us

Agent Zero is built for people who want to understand and shape their tools.

You can help by improving docs, creating skills, publishing plugins, testing model/provider setups, reporting bugs, sharing workflows, or contributing core improvements. Start with the Contributing guide, browse the Plugin Hub, or bring ideas to Discord.

Community and Support

• Discord for live discussion and help.
• Skool Community for community learning.
• YouTube for demos and tutorials.
• X, LinkedIn, and Warpcast for updates.
• GitHub Issues for bugs and feature requests.