Coding agents

Connect Warp

AI-native terminal (BYO inference, 2026). Point it at AgentKeyRoute so every request follows your governance profile and is recorded.

Get a key with the right protection
In the console, open Connect an app (opens in a new tab) and pick this tool. AgentKeyRoute recommends a governance profile, creates the key, and shows these same steps with your key and an allowed model filled in, plus a live test.

Setup

  1. Install Warp
    Install
    Download and install it from warp.dev.
  2. Point it at the gateway
    Warp · Bring Your Own Inference
    1. Settings → AI → Providers → Add Provider.
    2. Provider type:  OpenAI-compatible
    3. Base URL:       https://gateway.agentkeyroute.com/v1
    4. API Key:        <your API key>
    5. Model ID:       gpt-4.1
    6. Save, then pick the model in the Warp AI input bar.

    Replace <your API key> with your AgentKeyRoute key. gpt-4.1 is an example: use a model your key may use (GET /v1/models lists them).

  3. Check it works

    Start Warp and ask it something small, such as "list the files in this folder". The request appears in Requests (opens in a new tab) with the policy decision, the model that answered and what was redacted.

Good to know

  • The wizard marks this as a coding tool and adds Source code to its data. The recommended profile is usually Coding agents & developer tools.
  • It uses the OpenAI-compatible API, so the base URL ends in /v1.
  • If policy doesn't allow the model you chose for some data, the gateway answers with an allowed one. X-AIGov-Model names it.
  • Refused? See Why was a request blocked?