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

@appomni/n8n-nodes-agentguard

v0.1.2

Published

AppOmni's AgentGuard node

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

agentguard-appomniagentguard-appomni

Keywords

n8n-community-node-package

Readme

@appomni/n8n-nodes-agentguard

AppOmni AgentGuard provides runtime security for n8n workflows that leverage AI agents.

n8n is a fair-code licensed workflow automation platform.

Installation Operations Credentials Compatibility Usage Resources

Installation

Follow the installation guide in the n8n community nodes documentation.

Operations

| Resource | Operation | Description | |----------|-----------|-------------| | Prompt | Classify | Send a prompt to AppOmni for DLP and/or prompt firewall analysis. The node has two outputs (Allowed, Blocked). |

Credentials

Create an AgentGuard API credential with:

  • Tenant URL — the URL of your AppOmni tenant (e.g. https://example.appomni.com).
  • Ingest Token — your AppOmni-issued ingest token; sent as X-AppOmni-Ingest-Token.
  • Host override (optional) — overrides the X-Host header; leave blank unless instructed by AppOmni support.

Compatibility

Last tested against n8n 2.19.2.

Usage

Wire the node before any LLM call you want to protect:

Trigger → AgentGuard ─┬─ Allowed → LLM call
                                         └─ Blocked → log / alert / refuse

The output item carries an agentguard object with the verdict, the original prompt, and the full API response, ready for downstream nodes.

If the AppOmni tenant's policy includes a user_quarantine classifier, repeat-offender users can be temporarily locked out after a set number of strikes within a rolling window. For Chat Trigger workflows the node auto-populates User ID with the chat session ID, so users are quarantine-eligible by default — note that this scopes quarantine to the conversation, so starting a fresh chat session resets the strike count. For persistent identity across sessions (or for non-chat triggers), populate User ID, Username, or User Email under Additional Metadata explicitly — these resolve in that priority order, and any value you set there overrides the chat-session default. When a user is locked, AgentGuard returns response_action: "block" with block_reasons containing the quarantine reason — same shape as any other block, so the existing Blocked output handles it without extra wiring. Quarantine windows, strike counts, and lock duration are configured server-side per tenant; nothing needs to change in the workflow.

Resources