Skip to main content
A rig is a sandboxed VM tuned for coding agents. It is a shared workstation where agents and people can work in the same repository and environment. Each rig can include:
  • One or more agent harnesses, such as Claude Code, Codex, OpenCode, or Pi
  • Your Git repositories, dependencies, tools, and development services
  • Agent credentials, environment variables, and secrets
  • SSH access and URLs for exposed services
Amika provisions the VM, prepares it from your repository configuration, and connects it to the control plane. You can then operate the rig and its agents from the web UI, CLI, TypeScript SDK, HTTP API, chat integrations, or your editor.

​
Shared by agents and people

A rig is not only a background execution environment. You and your teammates can connect to it while agents are working. You can inspect files, run commands, open the repository in an editor, view services, and continue an agent session without moving the work to another machine. A single rig can run multiple agents at the same time. Rigs and their agents can also communicate with other rigs when work needs to span environments.

​
Persistent or temporary

Choose the lifetime that fits the task:
  • Temporary rigs start clean for a branch, pull request, check, or one-off task. Delete them when the work is complete.
  • Persistent rigs keep their filesystem and environment available for an ongoing project or durable automation. Stop them when idle and start them again later.
You can capture a configured rig as a snapshot to create more rigs from the same starting point.

​
Where rigs run

By default, rigs run on Amika’s hosted platform. Amika can also schedule rigs on infrastructure you connect, including your own computers or cloud environment. The control surface stays consistent across locations.

​
Rig and sandbox terminology

rig is the product term and the canonical CLI command. A rig is sandboxed compute, so sandbox, sandboxed, and sandboxing remain accurate when you describe its isolation or generic sandbox providers.
Some compatibility and configuration interfaces still use sandbox in exact identifiers. For example, amika sandbox remains a CLI alias, and repository configuration uses the [sandbox] table. Keep those identifiers as written when an example or reference page shows them.

​
Next steps

Create a rig

Provision a rig with your repository and agent credentials.

Rig lifecycle

List, stop, start, and delete rigs.

Connect to a rig

Open a shell or connect with an editor.

Configure a repository

Define reproducible rig settings alongside your code.