Getting Started

Set up with AI

The fastest way to get started. Pick whichever fits your workflow.

Skills — reviewable diff in minutes, no manual setup.

# Quick demo trace
npx skills add lmnr-ai/laminar-skills --skill laminar-quickstart-trace

# Instrument a real codebase
npx skills add lmnr-ai/laminar-skills --skill laminar-instrument-codebase

# Migrate from another observability tool
npx skills add lmnr-ai/laminar-skills --skill laminar-migrate-observability

Browse more at skills.sh · Source: lmnr-ai/laminar-skills

Once installed, prompt your LLM with something like: Set up Laminar in this repo.

Cursor rules — Laminar-aware completions in your editor.

pip install 'lmnr[all]'
lmnr add-cursor-rules

Creates .cursor/rules/laminar.mdc. Reload Cursor (Cmd+Shift+P → “Reload Window”) to activate. Or download directly.

Prompt Install

Incorporate Laminar into an existing productCopy

Best if you already have an LLM/agent pipeline and want high-quality traces (structure, context, tags, and privacy).

Basic install + auto-instrumentationCopy

Best if you just want traces to show up quickly with minimal code changes and provider spans captured automatically.

Migrate from another observability platformCopy

Best if you already use Langfuse/LangSmith/Helicone or custom OpenTelemetry and want a minimal-diff migration.

Manual install

pip install 'lmnr[all]'

npm install @lmnr-ai/lmnr

→ Tracing docs · Hosting options

---

Core setup

Whichever path you chose above, these are the two things happening under the hood.

Tracing

Add Laminar to your app and start capturing LLM and tool spans.

→ Tracing docs

Hosting

Choose between Laminar Cloud and self-hosting (and how to configure base URLs).

→ Hosting options