Loading page
Loading page
AI
Give an AI agent its own Linux workspace where it can research, write code and make documents for you.
Agent Zero is an AI agent that has a computer of its own. It gets a Linux workspace with a terminal, a browser and desktop apps. You give it a task in chat, and it works through the steps: search the web, write code, run it, and save the result as a file.
The agent runs in a sandbox, but you can watch and step in. You choose the model it uses. There is a main model for the conversation and a utility model for smaller jobs such as summaries.
Agent Zero is for people who want to try a general-purpose agent and see how it works. Developers can use it for small coding and data tasks. Researchers and writers can hand it a topic and ask for a document back. It needs some patience, because agents can make mistakes.
Running Agent Zero in your own service keeps its workspace, files and chat history with you. You use your own model keys, so you control which provider sees your prompts. On a server it is reachable from any browser, not only from one desktop.
The trade-off: a remote agent with a terminal is a serious tool. Keep AUTH_PASSWORD strong and private. Model use costs money with most providers, and long tasks use many tokens. You look after updates and backups of the workspace.
Containers: agent0ai/agent-zero:v1.9
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Agent Zero, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Agent Zero setup screen.