Connect LibreChat to Anoman AI

Step 1: Add a custom endpoint to librechat.yaml

Under endpoints.custom, add an Anoman entry with the OpenAI-compatible base URL and your API key. List the models you want to expose in the model picker.

endpoints:
  custom:
    - name: "Anoman"
      apiKey: "${ANOMAN_API_KEY}"
      baseURL: "https://api.anoman.io/v1"
      models:
        default: ["gpt-4o", "claude-sonnet-4-6", "claude-haiku-4-5"]
        fetch: false
      titleConvo: true
      titleModel: "gpt-4o-mini"

Step 2: Set the API key

Put your Anoman key in the LibreChat environment so the ${ANOMAN_API_KEY} reference resolves. Never commit the raw key.

# .env
ANOMAN_API_KEY=anm-sk-your-key-here

Step 3: Restart and select Anoman

Restart LibreChat and pick Anoman from the endpoint selector. Every message now routes through the gateway — guardrails run first, and usage is metered and traced per key.

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 LibreChat 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