CLOUDFLARE WORKER · 300+ POPS

Verify Agent Intent
At the CDN Edge

Before the payload ever hits your servers. Patent-pending phonetic folding catches evasion attempts that regex misses. Pure TypeScript. Zero dependencies. Sub-millisecond.

Deploy in 5 MinutesView on GitHub

Free on Cloudflare Workers free tier. 100K requests/month.

Why Regex Isn't Enough

Fraudsters misspell on purpose. Our 13-rule phonetic folding normalizes text before pattern matching.

Seseo
c(e/i) → s
"hace" → "ase"
Yeismo
ll → y
"calle" → "caye"
B-V merger
v → b
"vamos" → "bamos"
H-deletion
h → ∅
"huevon" → "uebon"
D-weakening
VdV → VV
"pagado" → "pagao"
Z → S
z → s
"transferenzia" → "transferensia"
// All of these match the same pattern:
"dame tu contraseña"
"dame tu contrasena"
"dame tu contrazena"
"dame tu kontrasenia"
// All fold to: "dame tu contrasena" \u2192 BLOCK (social_engineering, weight: 40)

Three Commands to Deploy

# Clone the worker
git clone https://github.com/MerchantGuard/cloudflare-llm-firewall
cd cloudflare-llm-firewall

# Deploy to Cloudflare (requires wrangler)
npx wrangler deploy

# That's it. Your edge firewall is live at:
# https://llm-firewall.<your-subdomain>.workers.dev

Built for the Edge

🌐

CDN Edge Execution

Runs as a Cloudflare Worker at 300+ PoPs worldwide. Screens messages before they reach your origin server. Zero cold starts.

⏱️

Sub-Millisecond

Aho-Corasick deterministic finite automaton runs in O(n) — linear in text length, regardless of pattern count. No regex backtracking.

🔊

13-Rule Phonetic Folding

Spanish normalization catches orthographic evasion that regex misses. "guevon", "huevon", "wuevon" all collapse to the same token.

🛡️

Prompt Injection Detection

"Ignore previous instructions", "forget your rules", "you are now" — caught at the edge before your LLM ever sees them.

💰

Fake Payment Detection

"Ya te pague", "ya te hice la transferencia" — pre-folded patterns catch misspelled and slang variants across 6 locales.

⚙️

Zero Dependencies

Pure TypeScript. No node_modules, no WASM, no external APIs. The entire verification layer ships as a single Cloudflare Worker bundle.

Edge Firewall vs. Sentinela API

Edge FirewallSentinela API
LayersL0 onlyL0 + L1 + L2 + L3
Latency<2ms<10ms
Patterns25 (open source)161 x 6 locales
ML ModelsNoneXLM-RoBERTa + XGBoost
Trust AdaptationNoYes (4 presets)
Hallucination DetectionNoYes (15-dim vectors)
DeploymentYour CloudflareOur API
CostCF free tier$0.003/call
Best ForFirst verification layerDeep analysis

Use both together: Edge Firewall verifies 85%+ of traffic at the CDN. Sentinela handles the rest with full ML cascade. Learn more about Sentinela →

Pricing

Open Source

$0

100K requests/month on Cloudflare Workers free tier. Deploy in 5 minutes. 25 patterns.

RECOMMENDED

Enterprise

Custom

Full 161-pattern pack. Dedicated workers. On-prem option. SLA. Scales to $10K-$25K+/mo or $0.0005/req at volume. 14-day POC.

FAQ

How is this different from Sentinela?+
Can I use both together?+
What patterns are included?+
Can I add my own patterns?+
What about latency?+

Your LLM Deserves a Trust Layer.

Three commands. Zero dependencies. Every message screened at the edge.

Deploy Now (Free)Full Sentinela API

Patent Pending · U.S. App. Nos. 63/983,615; 63/983,621; 63/983,843