agent-zero.ai valid

Agent Zero docs for LLMs

Agent Zero is a personal, organic agentic framework with a Web UI, Docker runtime, Browser and Desktop Canvas surfaces, projects, memory, plugins, skills, model presets, and optional host-machine connectivity through A0 CLI.

For agents: Agent Zero: personal agentic framework with Web UI, Docker runtime, browser and desktop canvases, memory, plugins, skills and optional host connectivity via A0

agent frameworkweb uidocker runtimebrowser automationollamaplugins

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-21T08:27:49.868Z. Cached copy · Source on agent-zero.ai

# Agent Zero docs for LLMs

Agent Zero is a personal, organic agentic framework with a Web UI, Docker runtime, Browser and Desktop Canvas surfaces, projects, memory, plugins, skills, model presets, and optional host-machine connectivity through A0 CLI.

## Start here

- [Installation](https://www.agent-zero.ai/p/docs/installation/): for desktop use, start with [Agent Zero Launcher](https://www.agent-zero.ai/p/docs/launcher/), create your first Instance, then select Open UI.
- [First-Run Onboarding](https://www.agent-zero.ai/p/docs/onboarding/): set up a cloud provider or a local Ollama model such as gemma4:26b with the guided wizard.
- Already in a terminal or deploying to a server? Use A0 Install: Windows PowerShell: `irm https://ps.agent-zero.ai | iex`; macOS/Linux: `curl -fsSL https://bash.agent-zero.ai | bash`.
- Optional host connector: Windows PowerShell: `irm https://cli.agent-zero.ai/install.ps1 | iex`; macOS/Linux: `curl -LsSf https://cli.agent-zero.ai/install.sh | sh`.

## Capability map

- Agent Zero is one Docker container with a full Linux system, Web UI, Browser, Desktop, Plugin Hub, and Skills.
- Use Desktop for GUI software, files, and LibreOffice Writer/Calc/Impress cowork in ODT, ODS, and ODP formats.
- Use Browser for live web pages, screenshots, forms, downloads, extensions, host-browser mode, and Annotate mode for targeted page comments.
- Use the Markdown Editor for plans, TODOs, notes, RFCs, and other text artifacts that should live outside chat history.
- Use Plugin Hub, MCP/A2A, custom prompts, tools, projects, and model presets to extend or specialize Agent Zero.
- Use Orchestrator with supported coding-agent backends, slash commands for repeatable actions, and per-chat goals for visible progress.
- Use A0 CLI when Agent Zero should work with host files, terminals, repositories, or an approved host browser while Agent Zero remains isolated in Docker.

## Practical guides

- [A0 CLI Connector](https://www.agent-zero.ai/p/docs/a0-cli-connector/): connect the host terminal, local files, and an approved host browser to Agent Zero.
- [Browser](https://www.agent-zero.ai/p/docs/browser/): use the Browser Canvas for web pages, screenshots, annotations, settings, and host-browser mode.
- [Desktop](https://www.agent-zero.ai/p/docs/desktop/): use the Desktop Canvas for GUI apps, files, and LibreOffice Cowork.
- [Projects](https://www.agent-zero.ai/p/docs/projects/): create focused workspaces with instructions, files, memory, variables, secrets, and Git repositories.
- [Model Presets](https://www.agent-zero.ai/p/docs/model-presets/): switch model setups for speed, cost, local work, or maximum capability.
- [Agent Profiles](https://www.agent-zero.ai/p/docs/agent-profiles/): create and manage profiles, edit prompts, set project availability, and control Tool, MCP, and Skill access.
- [Skills](https://www.agent-zero.ai/p/docs/skills/): pin focused procedures to a chat when a workflow needs repeatable instructions.
- [Plugins](https://w
…

Related sites

Other listed sites in AI agents and MCP. See the whole category →

Machine-readable: GET /v1/resolve?q=agent-zero.ai · GET /v1/domain/agent-zero.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for agent-zero.ai:
1. POST https://agentwebmap.com/v1/sites/agent-zero.ai/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://agent-zero.ai/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/agent-zero.ai/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/agent-zero.ai).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.