Skip to main content

​
OpenCode

OpenCode is a low-friction backend for users who want fast setup and an extensible local coding agent.

​
Install

Verify:

​
Models & providers

OpenCode is provider-flexible: point it at a hosted model, an OpenAI-compatible endpoint, or a local model if you want inference on your own hardware too. That makes it the most “local all the way down” option of the three CLI agents. Configure the model per agent in the Workbench.

​
Optional permission behavior

If you understand the tradeoff and want less interruption during agent work, configure OpenCode permissions according to your local policy. Example:
Only use broad permissions in repositories and machines where you’re comfortable with that level of autonomy.

​
Configure in Avibe

  1. Enable OpenCode on the setup wizard’s Choose your AI assistants screen, or later in Settings > Backends.
  2. Confirm the opencode CLI path on its card in Settings > Backends.
  3. Choose the working directory: open a project in the Workbench, or set a group’s Working Directory.
  4. Route one or more chat groups or direct messages to an Agent on OpenCode in Settings > Messaging Platforms > Groups or Direct Messages.

​
Best for

Fast iteration, lightweight tasks, and setups where you want inference local too. A common pattern routes your #frontend or quick-turnaround channels here — see Thread sessions for routing.