LLMVerify

Local-First Verification and Guardrails for LLM Inputs, Outputs, and Behavior.

You shipped an AI feature. Your LLM hallucinated a citation, leaked a customer's email, and followed a prompt-injection buried in user input — on the same day. LLMVerify is the safety layer that sits between your LLM and your users.

Versionv1.6.1

Packagellmverify

npmnpm

GitHub

LicenseMIT

Changelog

Verified 2026-08-22

$ npm install llmverify

What you get

One npm install. Zero telemetry. No API keys on the free tier. Everything runs locally — deterministic, pattern-based engines with no model calls and no network on the free tier.

Function	One-liner	What it does
verify(content)	await verify(aiResponse)	Runs hallucination, consistency, safety, and CSM6 checks; returns a risk level and findings
isInputSafe(input)	isInputSafe(userMessage)	Blocks prompt injection, jailbreaks, and malicious input before it reaches the model
redactPII(text)	redactPII(aiResponse)	Masks emails, phones, SSNs, credit cards, and API keys
containsPII(text)	containsPII(text)	Returns true if PII is present
detectAndRepairJson(...)	detectAndRepairJson(prompt, response)	Detects and repairs broken JSON output
monitorLLM(client)	monitorLLM(openaiClient)	Wraps any LLM client; tracks latency, token drift, and behavioral changes
sentinel.quick(...)	await sentinel.quick(client, model)	Runs regression tests against your model before users see changes
classify(...)	classify(prompt, response)	Intent detection, hallucination signals, and instruction compliance
auditLog(event)	auditLog({ ... })	Appends a local, hash-only audit entry for SOC 2 / HIPAA / GDPR evidence
run, prodVerify, ciVerify	await prodVerify(content)	Preset pipelines for dev, prod, strict, fast, and CI use

Tap a row to see description. Table is best viewed on larger screens.

Quick start (30 seconds)

Three lines of safety between your LLM and your users. No config file required. No API key required.

1. Install

$ npm install llmverify

2. Three lines of safety

const { verify, isInputSafe, redactPII } = require('llmverify');

// 1. Block prompt injection before it reaches the model.
if (!isInputSafe(userMessage)) {
  return { error: 'Invalid input detected' };
}

// 2. Verify the model's output.
const aiResponse = await yourLLM.generate(userMessage);
const result = await verify(aiResponse);

if (result.risk.level === 'critical') {
  return { error: 'Response failed safety check' };
}

// 3. Strip PII before the response reaches a user or a log.
const { redacted } = redactPII(aiResponse);
console.log(redacted);

Free tier: 500 verification calls per day (tracked locally, never sent anywhere). Same input plus same rules equals same result — every result carries an explicit limitations array.

How it works

LLMVerify runs deterministic, pattern-based engines locally — no model calls, no network on the free tier. Same input plus same rules equals same result. Every result carries an explicit limitations array stating what was and was not checked, so you never mistake a clean score for a guarantee.

Zero telemetry

Free tier makes zero network requests. No data leaves your environment.

Pattern-based

Deterministic engines - no probabilistic AI evaluating AI. Reproducible results.

Explicit limitations

Every result includes a limitations array. You always know what was not checked.

Runtime monitoring

monitorLLM wraps any client and tracks latency, token drift, and behavioral changes.

CLI

Verify from the terminal or start a local HTTP API for IDE / tool integration.

$ npx llmverify verify "The capital of France is London."

Verify a string from the terminal

$ npx llmverify-serve --port=9009

Start local HTTP API (localhost only by default)

$ npx llmverify-serve --host=0.0.0.0 --port=9009

Expose to network on trusted network only — no auth on the API

Server defaults

Binds to 127.0.0.1 by default, restricts CORS to localhost origins, and rate-limits clients (100 requests / 60s). Requires express (optional dependency that installs by default).

Framework Alignment

OWASP LLM Top 10NIST AI RMFEU AI ActISO 42001CSM6 (HAIEC 38-rule control set)

Baseline mapping only — not certification

Framework mappings describe alignment only. LLMVerify does not certify compliance with any framework. These mappings help you understand where LLMVerify checks fit within broader control objectives — they are not evidence of compliance.

What LLMVerify Cannot Prove

LLMVerify is a triage tool, not a truth oracle. Be honest with yourself about what it can and cannot do.

Cannot definitively prove hallucinations — signals are pattern-based, not ground-truth verification
Does not replace human review — use to triage, not to approve
PII detection is regex-based (~90% for standard formats, lower for variations)
Prompt-injection detection is pattern-based — novel or obfuscated injections can evade it
Free tier is 100% local — ML-enhanced features require paid tier and explicit API key
No MCP server — integration via SDK, CLI, or local HTTP only

Recommendation (not legal advice): Run verify() on every model output that reaches a user, and isInputSafe() on every user input that reaches a model. Treat the risk level as a triage signal, not an approval.

Integration: SDK, CLI, or local HTTP — not MCP

LLMVerify does not expose an MCP server. Integrate via the npm SDK, the npx llmverify CLI, or the local HTTP API (npx llmverify-serve). Do not fabricate MCP support.

Use with your tools

This package does not expose an MCP server. Integrate via the methods below.

CLI

$ npx llmverify verify "Your text here"

Local HTTP API

$ npx llmverify-serve --port=9009

SDK

$ npm install llmverify

const { verify, isInputSafe, redactPII } = require('llmverify');

const result = await verify(aiResponse);
if (result.risk.level === 'critical') {
  return { error: 'Response failed safety check' };
}

Copyable agent recipes

Verify AI output before showing to user

Run npx llmverify verify "<output>" and report the risk level. If risk is critical or high, do not show the output to the user without review.

Check user input for prompt injection

Use isInputSafe() from the llmverify SDK to check user input before sending it to the LLM. If it returns false, block the input.

Redact PII from AI response

Use redactPII() from the llmverify SDK to strip emails, phones, SSNs, credit cards, and API keys from the AI response before logging or displaying it.