sentinelproxy

n8n community node to mirror AI agent turns to SentinelProxy for self-healing evaluation (hallucination, prompt-injection, PII detection + auto-healed prompts).

Package Information

Released: 4 mo ago
Downloads: 17 weekly / 455 monthly
Latest Version: 0.1.2
Author: Tom Phillips

Available Nodes

SentinelProxy icon
SentinelProxy
Send an AI agent turn (system prompt, user input, response) to SentinelProxy for self-healing evaluation

Documentation

n8n-nodes-sentinelproxy

An n8n community node that mirrors each AI agent turn to
SentinelProxy — the self-healing layer
for AI agents. SentinelProxy's judge catches hallucinations, prompt injections,
PII leaks and competitor mentions, then hands you a hardened system prompt.

Installation

In n8n (self-hosted): Settings → Community Nodes → Install →
n8n-nodes-sentinelproxy.

Manually:

npm install n8n-nodes-sentinelproxy

Credential

Create a SentinelProxy API credential:

  • Project API Key — from your dashboard → project → Connect tab.
  • Base URL — leave as https://sentinelproxy.tomphillips.uk unless you
    self-host.

Usage

Add the SentinelProxy node immediately after your LLM / AI Agent node and map:

Field Map to
System Prompt your agent's system prompt
User Input the incoming user message
LLM Response the model's output
Latency (ms) the call latency, if available

The node POSTs to /api/v1/ingest, which acks instantly and evaluates the turn
asynchronously — it never blocks your workflow. PII is scrubbed at the edge
before anything is stored.

Develop

npm install
npm run build      # tsc → dist/, then copies the icon

Point n8n at the built package with N8N_CUSTOM_EXTENSIONS or link it into your
~/.n8n/custom folder. To get it into the verified registry, follow the
n8n community node submission guide.

License

MIT

Discussion