n8n-nodes-perf

n8n-nodes-perf

n8n community nodes for Perf AI — intelligent LLM routing, fact-checking, and schema validation for your automation workflows.

Nodes

Perf Chat

Send messages to any LLM with intelligent model routing. One node, any model.

• Intelligent Routing — Perf automatically selects the best model (GPT-5, Claude, Gemini, etc.) based on task complexity and cost
• Model Override — Pin to a specific model when needed
• JSON Mode — Get structured JSON output with optional schema enforcement
• OpenAI-Compatible — Drop-in replacement for vendor-specific LLM nodes

Perf Verify

Verify any text for factual accuracy before it reaches your users.

• Dual Output Routing — Automatically routes to "Verified" or "Issues Found" based on confidence thresholds
• Three Verification Modes — Fast (web search), Standard (web search + source analysis), Thorough (multi-pass deep verification)
• Auto-Correction — Returns a corrected version of the text with factual fixes applied
• Claim-Level Detail — See exactly which claims were verified, corrected, or flagged

Perf Validate

Validate JSON against a schema and auto-repair errors using AI-powered correction.

• Dual Output Routing — Routes to "Valid" or "Invalid" based on validation result
• Auto-Repair — Fixes type mismatches, missing fields, and format errors
• Strict Mode — Reject on any error instead of attempting repair

Installation

In n8n (Community Nodes)

• Go to Settings → Community Nodes
• Enter n8n-nodes-perf
• Click Install

Manual Installation

cd ~/.n8n/custom
npm install n8n-nodes-perf

Setup

• Sign up at dashboard.withperf.pro and create an API key
• In n8n, go to Credentials → New Credential → Perf API
• Paste your API key

Example Workflows

AI Email Response with Fact-Checking

Email Trigger → Perf Chat → Perf Verify → [Verified] → Send Reply
                                         → [Issues] → Human Review

Structured Data Extraction

Webhook → Perf Chat (JSON mode + schema) → Perf Validate → [Valid] → Database Insert
                                                          → [Invalid] → Error Queue

Research Report Pipeline

Schedule → HTTP (fetch sources) → Perf Chat → Perf Verify (thorough) → [Verified] → Slack

AI Agent Tool Support

All three nodes can be used as tools by n8n's AI Agent node (usableAsTool: true). Enable community node tool usage in your n8n instance settings.

Resources

• Perf API Documentation
• Perf Dashboard
• Report Issues

License

MIT