Stop sensitive data from leaking into LLM prompts.
PII redaction · Secret detection · Prompt injection blocking · Self-hosted via Docker.

Get Started · Docs · OSS vs Cloud · Managed Cloud

                           ┌─────────────────────────────┐
                           │        AISG Gateway          │
    ┌──────────┐           │                              │           ┌──────────────┐
    │          │  POST     │  1. Auth (API key)           │           │              │
    │ Your App ├──────────▸│  2. Resolve provider/model   │──────────▸│ LLM Provider │
    │          │           │  3. DLP scan (Presidio)      │           │ (Groq/OpenAI)│
    │          │◂──────────│  4. Block or redact           │◂──────────│              │
    └──────────┘  response │  5. Forward to upstream      │  response └──────────────┘
                           │  6. Return with metadata     │
                           │                              │
                           │         ┌──────────┐         │
                           │         │ Presidio │         │
                           │         │ (PII/NER)│         │
                           │         └──────────┘         │
                           └─────────────────────────────┘

AISG is an OpenAI-compatible proxy that acts as an AI firewall. It sits between your app and LLM providers, scanning every request for PII, secrets, and prompt injection attacks before anything reaches the model.

• PII Redaction — emails, phone numbers, credit cards, SSNs, names, locations, IP addresses
• Secret Detection — API keys, AWS credentials, GitHub tokens, private keys, Slack webhooks
• Prompt Injection Blocking — detects jailbreak and instruction override attempts
• Multi-Provider Routing — OpenAI-compatible API, BYOK, swap providers in config
• Fail-Closed Security — if the safety layer is down, requests are blocked, never forwarded unscanned
• Zero Cloud Dependencies — runs entirely on your machine via Docker

git clone https://github.com/aisecuritygateway/aisecuritygateway.git
cd aisecuritygateway
cp .env.example .env        # add your provider key
docker compose up --build   # gateway + presidio

curl http://localhost:8000/v1/chat/completions \
  -H "Authorization: Bearer change-me-to-a-real-secret" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [{"role": "user", "content": "My email is alice@acme.com and SSN is 123-45-6789"}]
  }'

The gateway redacts the email and SSN before forwarding. The response includes aisg_metadata.pii_detected: true.

13 entity types out of the box — the managed cloud extends this to 28+ with OCR image scanning.

• Fail-closed by default — if Presidio is unreachable, requests are blocked, never forwarded unscanned
• Auth by default — API key authentication enabled out of the box
• No telemetry — zero external calls, no analytics, no phone-home
• Secret scrubbing — structured logs automatically mask API keys and tokens
• Rate limiting — token bucket per API key (default 10 req/sec)

This repo gives you the core AI security proxy. The managed AI Security Gateway Cloud adds everything you need to run it across teams at scale.

Skip the setup? The managed version at aisecuritygateway.ai gives you everything here plus dashboards, multi-project policies, and 8 providers — no Docker required.

⭐ Star the repo · Learn more · Try the managed cloud

_{Security · License (Apache 2.0) · LinkedIn · X / Twitter · YouTube}

_{Built by Datum Fuse LLC — making AI safe by default.}