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

n8n-nodes-intersystems-iris

v0.1.0

Published

n8n community node to store AI agent chat memory in InterSystems IRIS over its Postgres wire protocol (iris-pgwire)

Downloads

217

Readme

n8n-nodes-intersystems-iris

An n8n community node that stores AI agent chat memory in InterSystems IRIS, using IRIS's PostgreSQL wire-protocol endpoint (iris-pgwire).

The table schema, message inserts, and reads all live in IRIS. The PostgreSQL client library is only used as the transport.

Nodes

  • IRIS Chat Memory — a Memory sub-node for the AI Agent. Persists the conversation history to an IRIS table, keyed by session, with a configurable context window.

Prerequisites

  • An InterSystems IRIS instance reachable over iris-pgwire.
  • n8n 1.x or later with community nodes enabled.

Installation

Follow the community node installation guide, or in n8n go to Settings → Community Nodes → Install and enter:

n8n-nodes-intersystems-iris

Credential: IRIS Pgwire API

| Field | Notes | | --- | --- | | Host | IRIS host running iris-pgwire | | Namespace | IRIS namespace (maps to the Postgres "database" concept), e.g. USER | | User | e.g. _SYSTEM | | Password | | | Port | iris-pgwire listener port (commonly 5432) | | SSL | disable / allow / require |

Usage

  1. Add an AI Agent node with a Chat Trigger.
  2. On the Agent's Memory input, add IRIS Chat Memory.
  3. Select (or create) an IRIS Pgwire API credential.
  4. Optionally set the Table Name (default n8n_chat_histories) and Context Window Length.

The table is created automatically on first use.

How it differs from the Postgres Chat Memory node

IRIS pgwire speaks the PostgreSQL protocol, but IRIS is a different database underneath. This node handles two protocol differences:

  • No JSON/JSONB column type. The stock LangChain Postgres history stores its message column as JSONB, which IRIS rejects. This node stores the serialized message in a wide VARCHAR and (de)serializes the JSON in JavaScript. LONGVARCHAR is avoided because over pgwire it reads back as a stream reference rather than inline text.
  • Zero-row DELETE. IRIS pgwire raises an error when a DELETE matches no rows; clearing an empty session is treated as a valid no-op.

Development

npm install
npm run build      # n8n-node build
npm run lint       # n8n-node lint
npm test           # vitest

License

MIT