> ## Documentation Index
> Fetch the complete documentation index at: https://59e2bec-opencomputer.manicule.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://59e2bec-opencomputer.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://59e2bec-opencomputer.manicule.dev/api/mcp.
> Every agent surface: https://59e2bec-opencomputer.manicule.dev/.well-known/llms-manifest.json

# Architecture (/getting-started/architecture)

<!-- agent-signals: reading_time_min: 1 · est_tokens: 266 · updated: 2026-11-11 -->
Related: [What is OpenComputer](/getting-started/introduction.md), [Quickstart](/getting-started/quickstart.md), [Develop locally](/getting-started/local-development.md)

> How Slack, the gateway, hosts and runners fit together

## The pieces

![How OpenComputer works](/_assets/acc223ff7a10c2e4e3fb1870b242191ba3f73bbe370fa14e6778255656789d86)

## Gateway

TODO

## Host agent

TODO

## Runner

TODO

## Where state lives

TODO

## Sandboxes only when you need them

Most platforms give every session its own sandbox, which sleeps and wakes up between turns. We tried that in early iterations of the product and ran into three problems:

* **It's slow.** Starting and resuming a session this way was too slow, even with several optimizations applied.
* **Cost scales linearly with sessions.** Every session pays for its own sandbox.
* **Most sessions don't need one.** Think of an exploratory session where you fix a few items in your docs: it doesn't need a separate sandbox and dedicated compute.

In many cases a shared VM can handle hundreds of concurrent sessions. A session only needs a sandbox when it runs a heavy build or spins up a preview environment, and at that moment OpenComputer delegates the session to the sandbox.