OpenClaw connects to Anoman as either an OpenAI- or Anthropic-compatible provider — pick whichever protocol your workflow prefers.

Prerequisites

An Anoman API key — create one in the dashboard (format anm-sk-…).
OpenClaw 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 (OpenAI-compatible)

In your OpenClaw provider config, add a provider that speaks the OpenAI Chat Completions protocol, pointed at Anoman.

# OpenClaw provider
api: "openai-completions"
baseUrl: "https://api.anoman.io/v1"
apiKey: "anm-sk-your-key-here"

Or use the Anthropic protocol

Prefer Claude-native tooling? Point OpenClaw at Anoman's Anthropic-compatible endpoint instead.

api: "anthropic-messages"
baseUrl: "https://api.anoman.io/anthropic"
apiKey: "anm-sk-your-key-here"

Pick a model

Reference any model in the Anoman catalog.

# Any Anoman model works, e.g.:
gpt-4o
gpt-4o-mini
claude-sonnet-4-6
claude-haiku-4-5

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 OpenClaw 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

Connect OpenClaw to Anoman AI