npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@jaswirraghoe/n8n-nodes-langwatch

v1.0.5

Published

LangWatch nodes for n8n - observability, evaluation, and prompt management for LLM applications

Readme

LangWatch + n8n

@langwatch/n8n-nodes-langwatch

This is an n8n community node. It lets you use LangWatch in your n8n workflows.

LangWatch is an LLM observability platform that provides tracing, evaluation, datasets, and prompt management.

n8n is a fair-code licensed workflow automation platform.

🚀 Recommended: Pair with Observability

For complete LangWatch integration, pair these nodes with @langwatch/n8n-observability to automatically trace your n8n workflows:

Observability Setup

Quick setup for self-hosted n8n via npm:

npm install -g @langwatch/n8n-observability
export EXTERNAL_HOOK_FILES=$(node -e "console.log(require.resolve('@langwatch/n8n-observability/hooks'))")
export N8N_OTEL_SERVICE_NAME=my-n8n
n8n start

Table of Contents

Installation

Self-hosted n8n

Follow the installation guide in the n8n community nodes documentation.

npm install @langwatch/n8n-nodes-langwatch

n8n Cloud

This is a verified community node. Search for LangWatch to use this node in n8n Cloud.

Operations

Dataset Batch Trigger

Emit one item per dataset row sequentially until done. Optionally initializes an experiment context for batch evaluations.

Key parameters:

  • Dataset Slug or ID
  • Experiment Configuration (enable, ID/Slug, Name, Workflow ID)
  • Row Processing Options: startRow, endRow, stepSize, limitRows/maxRows, shuffleRows/seed
  • Emit Interval (ms)

Output fields:

  • entry (your dataset row payload)
  • row_number, row_id, datasetId, projectId, timestamps
  • _progress { current, total, percentage, remaining }
  • _langwatch.dataset { id, rowId, rowNumber }
  • _langwatch.experiment and _langwatch.batch when experiment is enabled

Dataset Row Trigger

Fetch a single dataset row per execution while maintaining an internal cursor. Great for stepwise or scheduled processing.

Key parameters:

  • Dataset Slug or ID
  • Row Processing Options: startRow, endRow, stepSize, limitRows/maxRows
  • Reset Progress, Shuffle Rows, Shuffle Seed

Evaluation

Run evaluators and/or record results with multiple operation modes.

Operations:

  • Auto (Recommended) - automatically selects behavior based on inputs
  • Check If Evaluating - determines if running in evaluation context
  • Record Result - log a pre-computed evaluation result
  • Run and Record - execute an evaluator and log results
  • Set Outputs (Dataset) - write entries back to a dataset

Key parameters:

  • Run ID (optional override; otherwise inferred from _langwatch.batch.runId)
  • Evaluator selection (manual or dropdown)
  • Name, Evaluation Data, Evaluator Settings
  • Guardrail flags: asGuardrail, failOnFail
  • Dataset write: datasetSlug, format (standard/custom), mapping fields

Prompt

Retrieve and optionally compile a prompt from LangWatch Prompt Manager.

Key parameters:

  • Prompt selection: Manual (handle/ID) or Dropdown
  • Version selection: Latest or Specific version
  • Compile Prompt: Off/On
  • Variable Source: Manual, From Input Data, or Mixed
  • Strict Compilation: fail if required variables are missing

Variables:

  • Manual variables: list of name/value pairs (supports n8n expressions)
  • Input data variables: map template variable → input data path

Credentials

To use this node, you need to authenticate with LangWatch. You'll need:

  1. A LangWatch account at app.langwatch.ai
  2. API credentials from your LangWatch project settings: hostname and API key

How to create:

  1. In n8n, open Settings → Credentials → New
  2. Pick "LangWatch API"
  3. Fill endpoint and API key → Save → Test

Development

Prerequisites

You need the following installed on your development machine:

  • git
  • Node.js and npm. Minimum version Node 20. You can find instructions on how to install both using nvm (Node Version Manager) for Linux, Mac, and WSL here. For Windows users, refer to Microsoft's guide to Install NodeJS on Windows.
  • Install n8n with:
    npm install n8n -g
  • Recommended: follow n8n's guide to set up your development environment.

Build new version

npm run build
npm link

Test in local n8n

cd ~/.n8n/custom
npm link n8n-nodes-langwatch

Resources

License

MIT