Roo Code ships an OpenAI Compatible provider option. Point it at Anoman's /v1 endpoint so every autonomous edit, command, and chat turn passes through prompt-injection detection, PII masking, and content moderation first.

Prerequisites

An Anoman AI account with an active API key (anm-sk-...)
The Roo Code extension installed in VS Code

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.

Step 1: Open the provider settings

In the Roo Code panel, open Settings and change the API Provider to OpenAI Compatible. This exposes a base URL, API key, and model field.

Step 2: Enter the Anoman endpoint

Set the base URL to Anoman's OpenAI-compatible endpoint, paste your Anoman API key, and choose a model. Anoman routes the model name to the correct provider.

Base URL:  https://api.anoman.io/v1
API Key:   anm-sk-your-key-here
Model:     claude-sonnet-4-6

Step 3: Run an agent task

Give Roo Code a coding task. Because Roo Code sends tool calls in the request, Anoman's policy layer can allow or deny specific tools per your policy group in addition to the standard guardrails.

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 Roo Code 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 Roo Code to Anoman AI