Skip to main content
OpenComputer is a managed runtime for agents defined as code. A project can contain several agents. You write the behavior; OpenComputer manages development deployments, model execution, tools, durable sessions, streaming, and production versions.
The exported function is a reactive description of the agent. OpenComputer renders it for the current input and uses its return value as instructions for the managed agent loop. Hooks attach the model, tools, MCP servers, and subagents needed for that render.

Projects

Group multiple agents in one repository.

Reactive agents

Build agent behavior with a function and conditional hooks.

Deployments

Move immutable agent versions through Development and Production.

Sessions

Stream responses and inspect durable conversations.

Capabilities

Choose between tools, MCP servers, skills, and subagents.

Secrets

Declare secret-backed connections without exposing credentials to agents.

Logs

Follow agent and outbound-request activity from the CLI.

​
Start a project

The initializer creates one hello-world agent. The first watched deployment lets you create a cloud project or select an existing one, prints its dashboard URL, and syncs every configured agent to development.
There is no local agent server. Agent code runs in OpenComputer’s managed development cloud.

​
What is available today

  • TypeScript projects containing one or more agents
  • reactive instructions, model selection, tools, subagents, MCP servers, input metadata, and session data reads
  • cloud development with file watching and automatic synchronization
  • dashboard and CLI playground sessions
  • immutable deployments promoted through aliases such as production
  • project-level secrets with optional agent overrides and constrained outbound requests
  • indexed runtime and egress logs available from the CLI
Agent behavior belongs in the repository under opencomputer/. The dashboard is primarily for selecting environments, testing agents, and inspecting what was deployed.