CLI

Connect Hermes to Anoman AI

Hermes, the Nous Research terminal agent, connects to Anoman through a provider in its config — via the OpenAI Chat Completions or Anthropic Messages transport.

Prerequisites

An Anoman API key — create one in the dashboard (format anm-sk-…).
Hermes 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 Hermes' config.yaml, add a provider whose api points at Anoman and whose transport is chat_completions.

# config.yaml
providers:
  anoman:
    api: "https://api.anoman.io/v1"
    transport: "chat_completions"
    api_key: "anm-sk-your-key-here"

Or use the Anthropic transport

Point api at Anoman's Anthropic endpoint and set transport: anthropic_messages.

providers:
  anoman:
    api: "https://api.anoman.io/anthropic"
    transport: "anthropic_messages"
    api_key: "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 Hermes 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