CLI

Connect Goose to Anoman AI

Block's Goose routes through Anoman with its OpenAI provider. One gotcha: set the host WITHOUT /v1 — Goose appends the path itself.

Prerequisites

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

Configure the OpenAI provider

Set OPENAI_HOST to the Anoman host with NO /v1 suffix (Goose adds /v1/chat/completions), plus your key and the openai provider.

export GOOSE_PROVIDER=openai
export OPENAI_HOST=https://api.anoman.io
export OPENAI_API_KEY=anm-sk-your-key-here

Select a model and start a session

Run goose configure to choose the OpenAI provider and a model from the Anoman catalog, then start a session.

goose configure   # choose "OpenAI" + a model (e.g. gpt-4o)
goose session

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 Goose 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