Connect Zed to Anoman AI

Step 1: Set your API key

Provide your Anoman key to Zed's OpenAI provider. Zed reads the key from the OPENAI_API_KEY environment variable (or you can enter it in the assistant panel).

export OPENAI_API_KEY=anm-sk-your-key-here

Step 2: Point the OpenAI provider at Anoman

Open Zed settings (settings.json) and set the OpenAI provider's api_url to Anoman's OpenAI-compatible endpoint. Add the model(s) you want available in the assistant.

{
  "language_models": {
    "openai": {
      "api_url": "https://api.anoman.io/v1",
      "available_models": [
        { "name": "gpt-4o", "max_tokens": 128000 },
        { "name": "claude-sonnet-4-6", "max_tokens": 200000 }
      ]
    }
  }
}

Step 3: Use the assistant

Open the assistant panel and select an Anoman-backed model. Zed sends completions to the base URL; Anoman routes them to the right provider and applies guardrails before and after the call.

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 Zed 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