Skip to content

Add Laminar for Observability #6514

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
blackgirlbytes merged 1 commit into from
Feb 1, 2026
Merged

Add Laminar for Observability #6514

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added documentation/docs/assets/guides/laminar.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
57 changes: 57 additions & 0 deletions documentation/docs/tutorials/laminar.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
---
description: Integrate goose with Laminar to observe performance
---

# Observability with Laminar

This tutorial covers how to integrate goose with Laminar to trace your goose sessions and understand how the agent is performing.

## What is Laminar

[Laminar](https://laminar.sh/) is an open-source observability platform purpose-built for AI agents. It traces LLM calls, tool execution, and custom functions so you can debug, evaluate, and improve agent behavior.

## Why Laminar for goose

- High-signal traces for LLM calls, tools, and sub-agents.
- Replay any span in the Playground to compare prompts and models.
- Build datasets from production traces and run evaluations.
- Analyze trace patterns with natural language queries and dashboards.

## Set up Laminar

Sign up for Laminar Cloud at [laminar.sh](https://laminar.sh) or self-host Laminar from the [open-source repo](https://github.com/lmnr-ai/lmnr). Grab your project API key.

## Configure goose to export OTLP to Laminar

goose exports OpenTelemetry data over OTLP/HTTP. Point the exporter to Laminar and provide your API key as an authorization header.

### Laminar Cloud

```bash
export LMNR_PROJECT_API_KEY=lmnr_proj_...
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.lmnr.ai"
export OTEL_EXPORTER_OTLP_HEADERS="authorization=Bearer ${LMNR_PROJECT_API_KEY}"
export OTEL_EXPORTER_OTLP_TIMEOUT=10000
```

### Self-hosted Laminar

```bash
export LMNR_PROJECT_API_KEY=lmnr_proj_...
export OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:8000"
export OTEL_EXPORTER_OTLP_HEADERS="authorization=Bearer ${LMNR_PROJECT_API_KEY}"
```

If your self-hosted instance does not require auth, you can omit `OTEL_EXPORTER_OTLP_HEADERS`.

:::tip
If you do not see traces, try setting the endpoint to the explicit OTLP path, such as `https://api.lmnr.ai/v1/traces` or `http://localhost:8000/v1/traces`.
:::

## Run goose with Laminar enabled

Start goose normally. With the OTLP environment variables set, Laminar will capture traces of your goose sessions and tool execution.

_[Example trace (public) in Laminar](https://laminar.sh/shared/traces/63010af0-cf31-b8b6-0d77-fc9924bcaa4c)_

![goose trace in Laminar](../assets/guides/laminar.png)
Loading