Integrating Goose with HPC-AI Tech

Goose is an open-source AI agent that helps developers automate coding tasks, explore repositories, execute commands, and build intelligent development workflows. By connecting Goose to the HPC-AI Tech Model APIs platform, you can leverage high-performance models like MiniMax-M2.5 through a unified OpenAI-compatible API.

In this guide, we'll walk you through how to integrate Goose with HPC-AI Tech so you can start building with your preferred models in minutes.

cover

🚀 Prerequisites

Before we dive in, make sure you have:

  • Goose installed and configured

  • An HPC-AI Tech API Key (from the Model APIs platform)

🛠️ Configuration: Choose Your Method

Goose offers multiple ways to configure model providers depending on your workflow. Pick what suits you best.

Method 1: Interactive Configuration (Recommended)

Best for developers who prefer a guided setup.

Launch Goose.

Open Settings or Provider Configuration.

Select OpenAI-Compatible Provider.

Enter the following:

Base URL

https://api.hpc-ai.com/inference/v1

API Key

your-hpc-ai-api-key

Select the model:

minimax/minimax-m2.5

(You can replace this with any model available on the HPC-AI Tech Model APIs platform.)

Save the configuration and begin using Goose.

Method 2: Config File (The Structured Way)

Best for reproducibility, automation, or team environments.

Create or edit your Goose configuration file.

Configure the following:

{
  "provider": "openai-compatible",
  "baseURL": "https://api.hpc-ai.com/inference/v1",
  "apiKey": "${HPC_AI_API_KEY}",
  "model": "minimax/minimax-m2.5"
}

Using environment variables for your API key is recommended for improved security.

Method 3: Environment Variables (The Lightweight Way)

Best for quick setups or CI/CD pipelines.

export HPC_AI_API_KEY="sk-your-hpc-ai-api-key"
export OPENAI_API_BASE="https://api.hpc-ai.com/inference/v1"

Then launch Goose and select:

minimax/minimax-m2.5

as your default model.

✅ Verifying the Connection

After configuration, it's important to confirm everything is working correctly.

  • Restart Goose (if required)

  • Open a project or repository

  • Ask Goose to explain, generate, or modify code

  • Ensure responses are returned successfully from the model

A successful response confirms:

  • Your API key is valid

  • The endpoint is reachable

  • The model is correctly configured

🎯 Summary

By integrating Goose with HPC-AI Tech, you unlock:

  • Access to multiple state-of-the-art AI models

  • OpenAI-compatible APIs

  • Cost-efficient inference

  • Reliable, low-latency model serving

  • Flexible model switching through a single platform

Whether you're automating development tasks, building AI agents, or managing complex repositories, HPC-AI Tech provides the performance and flexibility needed to scale your workflows.

Happy coding!

Goose Integration with HPC-AI Tech