---
title: Integrating Goose with Langfuse
description: Learn how to integrate Goose, an open-source AI agent, with Langfuse for enhanced monitoring and automation of engineering tasks.
category: Integrations
sidebarTitle: Codename Goose
logo: /images/integrations/goose_icon.png
logoAppearance: dark
---

# Integrating Goose with Langfuse

[Goose](https://github.com/block/goose) is an open-source, on-machine AI agent that automates engineering tasks seamlessly. By integrating Goose with [Langfuse](https://langfuse.com), 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](https://github.com/block/goose)

## Get Started

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

<Steps>

### Set up Langfuse

Sign up for Langfuse Cloud [here](https://cloud.langfuse.com) or self-host Langfuse [Docker Compose](https://langfuse.com/self-hosting/deployment/docker-compose) to get your Langfuse API keys.

### Configure Goose to Connect to Langfuse

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

```bash
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 Langfuse 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 Langfuse Integration

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

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

_[Example trace (public) in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/cea4ed38-0c44-4b0a-8c20-4b0b6b9e8d73?timestamp=2025-01-31T15%3A52%3A30.362Z&observation=7c8e5807-3c29-4c28-9c6f-7d7427be401f)_

  ![Goose trace in
  Langfuse](/images/docs/goose-integration/goose-example-trace.png)

</Steps>

## Demo

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

<iframe
  width="100%"
  className="aspect-[16/9] rounded border w-full"
  src="https://www.youtube-nocookie.com/embed/W39BQjsTS9E?si=wLDFwDmfMBEOHQ2A"
  title="YouTube video player"
  frameBorder="0"
  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
  referrerPolicy="strict-origin-when-cross-origin"
  allowFullScreen
></iframe>

## References

- **Goose Docs:** [https://block.github.io/goose/docs/category/getting-started](https://block.github.io/goose/docs/category/getting-started)
- **Langfuse Docs:** [https://langfuse.com/docs](https://langfuse.com/docs)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/no-code/goose.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.