Goose

Use TensorX models with Goose — the open-source, on-machine AI agent by Block (Square).

---

Overview

Goose is an open-source agent by Block with support for declarative custom providers.

---

Prerequisites

• macOS, Linux, or Windows

• A TensorX API key (sign up here)

---

Installation

macOS (Homebrew)

brew install block/tap/goose

Linux / macOS (curl)

curl -fsSL https://github.com/block/goose/releases/latest/download/download_cli.sh | bash

Desktop App

Download from block.github.io/goose

---

Configuration

Option 1: Using OpenAI-Compatible Provider

Set environment variables and configure Goose:

export TENSORX_API_KEY=your-tensorx-api-key-here

Then configure via the CLI:

goose configure

When prompted:

1. Choose OpenAI Compatible as the provider

2. Enter https://api.tensorx.ai/v1 as the base URL

3. Enter your model name: z-ai/glm-5.3

Option 2: Settings File

Edit ~/.config/goose/config.yaml:

GOOSE_PROVIDER: openai-compatible
GOOSE_MODEL: z-ai/glm-5.3
OPENAI_BASE_URL: https://api.tensorx.ai/v1
OPENAI_API_KEY: your-tensorx-api-key-here

Replace your-tensorx-api-key-here with your actual TensorX API key from app.tensorx.ai.

---

Model selection

Call GET /v1/models with your TensorX API key and use one of the returned IDs. If the integration depends on a capability or token limit, query GET /v1/model/info before selecting the model. See Models for examples.

---

Usage

Start an interactive session:

goose session

Or run a one-shot command:

goose run "refactor the auth module to use JWT tokens"

Goose can:

• Read and edit files in your project

• Run terminal commands

• Search your codebase

• Connect to external tools via MCP extensions

---

Troubleshooting

Model Not Responding

1. Verify your API key: echo $TENSORX_API_KEY

2. Test the connection:

   curl https://api.tensorx.ai/v1/models \
     -H "Authorization: Bearer $TENSORX_API_KEY"

Provider Not Found

Run goose configure to reconfigure your provider settings.

---

See Also

• Goose Documentation

• Goose on GitHub

• Goose Custom Providers

• TensorX Models