ZuploZuplo
LoginStart for Free
  • Documentation
  • API Reference
Introduction
Getting Started
    Develop in the portal
      1 - Setup Your Gateway2 - Rate Limiting3 - API Key Auth4 - Deploy5 - Dynamic Rate LimitingDynamic MCP Server - Quickstart
    Develop locally with the CLI
      1 - Setup Your Gateway2 - Rate Limiting3 - API Key Auth4 - Deploy5 - Dynamic Rate LimitingDynamic MCP Server - Quickstart
Concepts
Development
Policies
Handlers
API Keys
Rate Limiting
Caching
MCP Server
MCP Gateway
AI Gateway
    IntroductionGetting StartedSource ControlUniversal API
    Providers
    Teams
    Apps
    Policies
    Cookbooks
    Integrations
      AI SDKClaude CodeCodexGooseLangChain SDKOpenAI SDK
Developer Portal
Monetization
GraphQL
Deploying & Source Control
Analytics
Observability
Networking & Infrastructure
Account Management
Programming API
Build with AI
Zuplo CLI
Migration Guides
Platform LimitsVersion Support PolicySecuritySupportTrust & ComplianceChangelog
powered by Zudoku
Integrations

goose

goose is a local AI agent and CLI tool for automating engineering tasks. It's completely open-source with no vendor lock-in, supports local LLMs, has extensive MCP (Model Context Protocol) support, and offers powerful extensibility through recipes.

Prerequisites

In order to use the AI Gateway with goose you will need to complete these steps first:

  1. Create a new provider in the AI Gateway for the provider you want to use with goose

  2. Set up a new team

  3. Create a new app to use specifically with goose and assign it to the team you created

  4. Copy the API URL and API Key shown at the top of the app page

Configure goose

Because goose can be run as a standalone desktop app and a CLI there are two configuration approaches depending on which version you choose.

CLI

  1. Run goose configure

  2. Select Configure Providers from the menu

  3. Choose OpenAI as the provider you want to add (this will work for any OpenAI compatible provider and model)

  4. Set the OPENAI_API_KEY to the API Key for the app you created for goose in Zuplo

  5. Set the OPENAI_HOST to your app's gateway URL without the /v1 suffix (for example https://my-gateway-main-2e18f50.zuplo.app/config_fe0a04972d2848e0a94ae4b8bcd1497e)—the base path in the next step supplies it

  6. The OPENAI_BASE_PATH may already be configured. If it's not, enter v1/chat/completions as the value

  7. Enter the model you want to use with goose, as providerName/model—for example openai/gpt-5-mini.

The app's Model Filtering policy controls which models the app may use, so the model you enter here must be one that policy allows.

After completing the steps, goose will check the configuration. If all is well it will save the configuration and you are ready to start working with goose via the AI Gateway.

Desktop App

If you are using the goose desktop app you can add a Custom Provider for AI Gateway by following these steps:

  1. Open the goose desktop app

  2. Click on Settings

  3. Click on Configure Providers to open the Provider settings

  4. Click on Add Custom Provider

  5. Choose a Provider Type (both OpenAI Compatible and Anthropic compatible will work)

  6. Enter a Display Name (for example Zuplo AI Gateway)

  7. Set the API URL to your app's gateway URL

  8. Set the API Key to the API key of the app you created for goose in Zuplo

  9. Set the list of Available Models to the models the app's Model Filtering policy allows, named as providerName/model (for example openai/gpt-5-mini, openai/gpt-5, openai/gpt-5-nano)

  10. Click on Create Provider

The Zuplo AI Gateway and associated provider and models will now be available to use with the goose desktop app.

Edit this page
Last modified on August 18, 2026
CodexLangChain SDK
On this page
  • Prerequisites
  • Configure goose
    • CLI
    • Desktop App