Goose

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

Overview

Goose is an open-source AI agent built by Block (formerly Square) that runs on your machine and helps with coding, DevOps, and general development tasks. With 32K+ GitHub stars and support for declarative custom providers, it's easy to connect to TensorX.

Why Goose + TensorX?

🪿 On-machine agent — Runs locally, full access to your filesystem and tools
🔌 MCP support — Connect to any tool via Model Context Protocol extensions
🖥️ Desktop + CLI — Electron desktop app and terminal interface
🔒 Privacy-first — Your code stays on your machine, EU-hosted models
💰 Cost-effective — Powerful open-source models at a fraction of the cost

Prerequisites

macOS, Linux, or Windows
A TensorX API key (sign up here)

Installation

brew install block/tap/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:

Choose OpenAI Compatible as the provider
Enter https://api.tensorx.ai/v1 as the base URL
Enter your model name: z-ai/glm-5.1

Option 2: Settings File

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

GOOSE_PROVIDER: openai-compatible
GOOSE_MODEL: z-ai/glm-5.1
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.

Recommended Models

Use Case

Model

Why

Coding ⭐

z-ai/glm-5.1

Best coding performance, strong reasoning

Reasoning

deepseek/deepseek-r1-0528

Complex analysis and planning

Functions

minimax/minimax-m2.5

Function calling, reasoning

Vision

moonshotai/kimi-k2.5

Image understanding, large context

General

deepseek/deepseek-chat-v3.1

Balanced performance and cost

Fast

minimax/minimax-m2

Quick responses, cost-sensitive

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

Verify your API key: echo $TENSORX_API_KEY

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.

Good afternoon