Build and secure your AI applications

ML models, typed SDKs, and drop-in integrations for n8n, LiteLLM, and custom stacks.

Models, SDKs, and integrations

Every component of Vigil Guard's detection stack, available standalone.

VGE PromptGuard v1g

The detection engine behind Vigil Guard Enterprise. 44M-parameter model with native English and Polish support, code-aware classification, and extended coverage for 5+ additional languages.

0.981 F1 on direct prompt injection detection
97.5% agentic attack detection across tool outputs, API responses, and function returns
Sub-1% false positive rate in production workloads
2× overall F1 vs base model on Protect AI validation set (0.934 vs 0.452)
Code-native: trained on source code from MLM phase, catches injections in code contexts
ONNX-optimized for real-time CPU inference (44M parameters)

Python SDK

Official Python SDK for Vigil Guard Enterprise

from vigil_guard import VigilClient

client = VigilClient(api_key="...")

result = await client.guard(prompt)

Full API access
Async support
Type hints & documentation
Policy management

LiteLLM Guardrail Adapter

Drop-in guardrail integration for LiteLLM Proxy. Protect every model behind a single gateway

LiteLLM guardrail integration showing benign request and injection detection scenarios

Easy-config LiteLLM Proxy integration
Pre-call & post-call guardrailing
ALLOW / SANITIZE / BLOCK decisions
Fail-closed by default (safety-first)
Docker-ready with security hardening

n8n Verified Community Node

Verified and available on n8n Cloud and n8n On-Prem since March 21, 2026. Add VigilGuard AI security directly to your workflows from the canvas.

n8n workflow with Vigil Guard input and output guard nodes protecting an AI agent

Visual workflow builder
Protect AI agents at runtime
ALLOW / SANITIZE / BLOCK actions
No coding required

You can't secure what you don't see.

AI is already part of your environment. Vigil Guard makes it visible, controllable and safe.