Sign inSign up

sbx/opencode-model-runner-kit

Verified Publisher

By Docker, Inc

•Updated 8 days ago

OpenCode wired to a local Docker Model Runner instance via its OpenAI-compatible API, with automa...

Sandbox Kit
0

5.6K

sbx/opencode-model-runner-kit repository overview

Base Imagedocker/sandbox-templates:opencode-docker
Digest

sha256:1bd0658996cd…

Size

2 Bytes

Schema

v2

Pushed

8 days ago

Specificationspec.yaml
SANDBOX KIT

OpenCode wired to a local Docker Model Runner instance via its OpenAI-compatible API, with automatic model discovery.

Network Egress

host.docker.internal:12434

registry.npmjs.org

Run in a Sandbox

sbx run opencode-model-runner --kit docker.io/sbx/opencode-model-runner-kit:latest

Make sure you have docker sbx installed

Run the following command to install sbx on your machine.

macOS
brew install docker/tap/sbx
Windows
winget install Docker.sbx
Learn more about docker sbx⁠

⁠opencode-model-runner

A fork of the built-in opencode agent that routes all model API calls to a local Docker Model Runner⁠ instance via its OpenAI-compatible endpoint. Useful for offline development, cost-free experimentation, or testing custom local models with the OpenCode UI.

Prerequisites: Docker Model Runner must be enabled on the host with TCP access on port 12434, and at least one model must be pulled:

$ docker desktop enable model-runner --tcp
$ docker model pull <model>

Linux hosts: host.docker.internal requires Docker to be started with --add-host=host.docker.internal:host-gateway. If Model Runner is unreachable, verify this flag is set or use your host's LAN/bridge IP in place of host.docker.internal.

⁠Usage

sbx run --kit "docker.io/sbx/opencode-model-runner-kit:latest" opencode-model-runner ~/my-project

Or from a git URL or a local clone of this repo:

sbx run --kit "git+https://github.com/docker/sbx-kits-contrib.git#dir=opencode-model-runner" opencode-model-runner ~/my-project
sbx run --kit ./opencode-model-runner/ opencode-model-runner ~/my-project

The agent name passed to sbx run (opencode-model-runner) matches the name: field in the kit's spec.yaml.

All models available via docker model ls are automatically discovered and selectable in OpenCode via /models.

⁠How it works

OpenCode reads its provider configuration from ~/.config/opencode/opencode.json. This kit uses commands.initFiles to drop that JSON into the sandbox at startup, declaring:

  • An @ai-sdk/openai-compatible provider (dmr) whose baseURL is http://host.docker.internal:12434/v1 (Model Runner's OpenAI-compatible endpoint), with modelsDiscovery.enabled: true so the provider queries Model Runner's /models endpoint at startup.
  • The opencode-models-discovery plugin (with smartModelName: false) which surfaces the discovered models in OpenCode's model picker.

Any model pulled with docker model pull appears automatically — no manual config edits needed.

⁠Related