Integrating Goose with Neural Inverse

Goose is an open-source, on-machine AI agent that automates engineering tasks seamlessly. By integrating Goose with Neural Inverse, you can monitor your Goose requests and understand how the agent is performing.

About Goose

Goose is a powerful, open-source AI agent that runs locally on your machine to automate common engineering workflows. It's designed to help developers spend more time building and less time on repetitive tasks.

Core capabilities:

Fully open source and extensible, enabling you to customize Goose for your specific needs
Local-first architecture that keeps you in control of execution and data
Flexible integration options with your preferred LLM providers and Model Context Protocol (MCP) servers
Built-in intelligence to handle complex engineering tasks with minimal supervision

Here are some real-world examples of how developers use Goose:

Generate comprehensive test data that accurately reflects complex API business logic
Build automation scripts for Google Workspace to streamline team coordination
Execute large-scale codebase migrations, such as React component updates
Create and manage custom CLI tools to optimize development workflows

GitHub: https://github.com/block/goose

Get Started

This guide will walk you through the steps to integrate Goose with Neural Inverse.

Set up Neural Inverse

Configure Goose to Connect to Neural Inverse

Set the environment variables so that Goose (written in Rust) can connect to the Neural Inverse server.

export LANGFUSE_INIT_PROJECT_PUBLIC_KEY=pk-lf-...
export LANGFUSE_INIT_PROJECT_SECRET_KEY=sk-lf-...
export LANGFUSE_HOST=https://cloud.langfuse.com # EU data region 🇪🇺

# Other Neural Inverse data regions: https://us.cloud.langfuse.com (🇺🇸 US), https://jp.cloud.langfuse.com (🇯🇵 Japan), https://hipaa.cloud.langfuse.com (⚕️ HIPAA)
# https://localhost:3000 if you're self-hosting

Run Goose with Neural Inverse Integration

Now, you can run Goose and monitor your AI requests and actions through Neural Inverse.

With Goose running and the environment variables set, Neural Inverse will start capturing traces of your Goose activities.

Example trace (public) in Neural Inverse

Demo

Alice (Goose) and Marc (Neural Inverse) demo how Neural Inverse enables observability into Goose's actions—letting you trace LLM behavior and catch errors on the Goose YouTube channel:

References

Goose Docs: https://block.github.io/goose/docs/category/getting-started
Neural Inverse Docs: https://langfuse.com/docs

Was this page helpful?

On this page