AI Cyber Central · LLM Firewall
Free · Self-hosted · Open download

Put a firewall in front of your LLM calls — in minutes.

Screen every prompt and completion for prompt injection, jailbreaks, PII, and secret leakage. An OpenAI-compatible proxy that runs entirely on your own infrastructure. No prompt ever leaves your box.

Zero egressOne Docker commandAny providerNo telemetry

Get the free download

The full LLM Firewall — binary + Docker image. We'll email you the link.

The firewall is zero-egress. This form is the only thing that ever collects your details.

Check your inbox

We've sent your download link and quick-start. It's on its way.

↓ Download now

Want it wired into advisory, policy, assurance, risk & inventory with a full control plane? See the Cyber Suite →

What it catches

Bidirectional, in-line, on-prem — the same detection engine that ships inside the AI Cyber Central suite, as a standalone you can run today.

Ingress

Prompt injection & jailbreaks

Direct and indirect injection, role-play and refusal-suppression jailbreaks — normalised past base64 and homoglyph obfuscation before scanning.

Data

PII & secret leakage

Redact emails, IDs, keys and tokens before they reach the model — and catch secrets on the way back out.

Egress

Unsafe output

Screen completions for harmful content and exfiltration channels before the answer reaches your app.

Control

Monitor, then enforce

Start in monitor mode to tune with zero risk, then flip to enforce — allow, redact, rewrite, or block.

Built by a security company — and it shows.

The firewall makes no outbound call except to your model provider. No analytics, no phone-home. Map every control to the frameworks your auditors already use.

OWASP LLM TOP 10 · MITRE ATLAS · NIST AI RMF · EU AI ACT
Explore the full Cyber Suite →