Skip to main content

Secure Your LLM Infrastructure with PrivyGate

The open-source AI Firewall designed for Southeast Asia. Anonymize PII, comply with PDPA, and keep your customer data within your VPC while leveraging the power of OpenAI, Claude, and Gemini.

Zero Data Leakage

We intercept requests before they leave your network. PII like Names, Phones, NRIC, and Credit Cards are replaced with semantic fakes.

SEA Localized

Built-in support for Singapore NRIC, Indonesia NIK, Thai ID, and multi-language NER (English, Chinese, Bahasa, Thai).

Reversible & Seamless

Responses are automatically "de-anonymized". Your application sees the real data; the public LLM only sees the fake data.

Drop-in Replacement for OpenAI

No need to rewrite your application. Just change the base_url and point it to your internal PrivyGate instance.

  • Compatible with LangChain, AutoGen, & LlamaIndex
  • Supports streaming responses
  • Enterprise Audit Logs (PDPA ready)
from openai import OpenAI

# Point to your PrivyGate instance client = OpenAI( base_url=“http://privygate-internal:8000/v1”, api_key=“any-string” )

# Send sensitive data safely response = client.chat.completions.create( model=“gpt-4”, messages=[ {“role”: “user”, “content”: “My name is Tan Wei Ming, NRIC S1234567Z…”} ] ) # PrivyGate handles the rest!

Choose Your Protection Level

FeatureCommunity (Free)Enterprise
PII AnonymizationBasic (En/Zh)Advanced (SEA Languages)
PerformanceUp to 100 QPSUnlimited (Go Engine)
DeploymentDocker ComposeKubernetes / Helm
Compliance Reports-PDF / JSON Audit
SupportGitHub Issues24/7 Dedicated

Ready to secure your AI?

Start with our open-source version today, or contact us for a Proof of Concept (PoC) in your environment.