Connect Zed to Anoman AI
Zed's AI assistant supports OpenAI-compatible providers via a custom api_url in settings.json. Point it at Anoman to add the full guardrail pipeline and observability to every inline assist and chat request.
Prerequisites
- An Anoman AI account with an active API key (
anm-sk-...) - Zed installed (zed.dev)
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: Set your API key
Provide your Anoman key to Zed's OpenAI provider. Zed reads the key from the OPENAI_API_KEY environment variable (or you can enter it in the assistant panel).
Step 2: Point the OpenAI provider at Anoman
Open Zed settings (settings.json) and set the OpenAI provider's api_url to Anoman's OpenAI-compatible endpoint. Add the model(s) you want available in the assistant.
Step 3: Use the assistant
Open the assistant panel and select an Anoman-backed model. Zed sends completions to the base URL; Anoman routes them to the right provider and applies guardrails before and after the call.
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 Zed requests — PII masking and content moderation apply automatically, and prompt injection is scored when capacity allows.
Need help with your integration?
Reach the Anoman team directly with questions about your setup.