CLI

Connect opencode to Anoman AI

opencode adds providers through the AI SDK. Register Anoman as an OpenAI-compatible provider (or Anthropic) in your opencode config.

Prerequisites

An Anoman API key — create one in the dashboard (format anm-sk-…).
opencode installed and up to date.
A model ID from the Anoman catalog, e.g. gpt-4o, gpt-4o-mini, or claude-sonnet-4-6.

Enable streaming for long agent runs

Set stream: true on requests. Autonomous, multi-step, and long-thinking tasks can exceed the 100-second edge timeout and fail with a 524 error; streaming returns tokens as they are generated and keeps the connection alive, so the request completes. Most tools stream by default — confirm it is on for agentic use.

More detail in the streaming guide.

Add Anoman as a provider

In opencode.json, register a provider using @ai-sdk/openai-compatible with Anoman's base URL and your key.

// opencode.json
{
  "provider": {
    "anoman": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.anoman.io/v1",
        "apiKey": "anm-sk-your-key-here"
      },
      "models": { "gpt-4o": {}, "claude-sonnet-4-6": {} }
    }
  }
}

Prefer Anthropic?

Swap the npm package to @ai-sdk/anthropic and point baseURL at Anoman's Anthropic endpoint.

"npm": "@ai-sdk/anthropic",
"options": {
  "baseURL": "https://api.anoman.io/anthropic",
  "apiKey": "anm-sk-your-key-here"
}

Verify the guardrails are active

Every Anoman response carries guardrail result headers. Inspect them in your dashboard traces to confirm the pipeline is running on opencode requests — prompt-injection detection, PII masking, and content moderation all apply automatically.

X-Anoman-Guardrail-Injection: pass score=0.03
X-Anoman-Guardrail-Pii: pass
X-Anoman-Guardrail-Content: pass
X-Anoman-Cache: none

Need help with your integration?

Join the Founding 50 for early access and direct support from the Anoman team.

Join Founding 50