Harnesses
Console works with coding agents other than OpenCode. Point a harness at the Console gateway with an API key to use any paid or Go model, and usage is billed to your workspace like any other request.
| Harness | Pay-as-you-go | Go | MCP |
|---|---|---|---|
| Claude Code | Yes | Yes | Yes |
| Codex | Yes | Yes | Yes |
| Hermes | Built in | Built in | Yes |
| Pi | Built in | Built in | Yes |
| Raycast | Extension | Extension | Yes |
Free-tier chat models are only available from within OpenCode. Other harnesses receive HTTP 403 for those models,
even with a Console API key. Use paid models or a Go subscription.
The Console CLI connects a harness to your workspace with one command. It needs Node.js 22 or later.
| Harness | Command |
|---|---|
| Claude Code | npx @opencode/console setup claude-code |
| Codex | npx @opencode/console setup codex |
| Hermes | npx @opencode/console setup hermes |
| Pi | npx @opencode/console setup pi |
| DeepSeek Harness | npx @opencode/console setup deepseek-harness |
Your browser opens Console, where you approve the sign-in and pick the workspace. The harness then gets
- the workspace’s models, through Console
- the workspace’s policies, checked before every tool call
- the workspace’s MCP servers, skills and instructions
The CLI keeps the harness in sync with the workspace and updates itself.
To keep a harness’s own sign-in and models, such as a Claude or ChatGPT subscription, add --keep-provider. The harness
still gets the workspace’s policies, MCP servers, skills and instructions. It works with Claude Code, Codex and Hermes.
npx @opencode/console setup codex --keep-providerTo set up a harness by hand, or one the CLI doesn’t cover, use an API key and the base URLs below.
Harnesses authenticate with a Console API key. The quickest option is a personal API key, which calls models as you.
- Open Account from the account menu in the Console.
- Under Personal API keys, click Add API key.
- Choose the workspace, name the key, and click Create.
- Copy the key. It is shown only once.
oc_sk_1a2b3c4d5e6f_...Usage counts toward your member budget. Use a key from a workspace with credits for pay-as-you-go, or from a workspace subscribed to Go for Go.
For shared machines or CI, owners and admins can create a service account key instead, so usage isn’t tied to one person.
Pay-as-you-go and Go are served from different base URLs. Use the one that matches your plan.
| Plan | Base URL |
|---|---|
| Pay-as-you-go | https://opencode.ai/inference |
| Go | https://opencode.ai/inference/go |
Append the path for the API your harness speaks. Every API serves every paid and Go text model: Console sends a request to the model’s own endpoint when it speaks that API, and translates it otherwise.
| API | Path |
|---|---|
| OpenAI Responses | /openai/v1/responses |
| OpenAI Chat Completions | /openai/v1/chat/completions |
| Anthropic Messages | /anthropic/v1/messages |
| Gemini | /google/v1beta/models/<model>:generateContent |
https://opencode.ai/inference/go/openai/v1/chat/completionsSend a stable session ID with every request so Console can route a conversation consistently and reuse its prompt cache. Go requires it.
x-opencode-session: ses_...Console also recognizes the native session headers sent by Claude Code, Codex, Hermes, and Pi, so they need no extra configuration.
Harnesses with MCP support can manage your workspace through the Console MCP server. It uses OAuth with dynamic client registration, so you sign in from the browser instead of pasting a key.
https://opencode.ai/console/mcpEach harness page shows how to add it. OpenCode adds the server automatically as opencode_console when your workspace
enables it, and asks you to sign in from the browser the first time it uses it.