Stop prompt injection before it reaches your LLM
AgentGuards is a drop-in guardrail layer for AI apps and coding agents — prompt injection, jailbreak, PII, secret, and data-exfiltration checks on every request, with per-tenant config and audit logs.
Defense in depth for every prompt
Layered checks run on each request and short-circuit on the first real threat.
Prompt injection & jailbreak
Heuristic patterns, an optional LLM judge, and Meta's PromptGuard ML model catch instruction-override and jailbreak attempts before they reach your model.
PII & secret redaction
Detect and redact emails, SSNs, credit cards, API keys, and tokens in prompts and tool inputs.
Data exfiltration & restricted topics
Block attempts to siphon data or steer the agent into off-limits territory, with policy-as-code you control.
Web-content defense
Purpose-built checks for fetched web pages — hidden text, HTML-comment injection, and XSS-as-injection vectors.
Per-tenant config & audit logs
Every customer gets isolated checks, their own keys, and a queryable audit trail of every decision.
Bring-your-own model key
Run the LLM-judge check on your own OpenAI key — your traffic, your spend, full control.
Pricing that scales with you
AgentGuards meters real work — guardrail checks — so you only pay as your product grows. No seats, no upfront commitment.
- ◆You pay for what you scan — guardrail checks per month, nothing upfront.
- ◆Easy to meter: requests, tokens scanned, and blocked events.
- ◆Low barrier to start — no commitment, generous free tier.
- ◆Scales with your growth, so our pricing tracks your success.
Simple, usage-based plans
Start free. Upgrade when your traffic does.
Free
Kick the tires on real traffic.
- ✓5k requests / mo
- ✓1 API key
- ✓All core checks
- ✓Community support
Bronze
For early-stage projects.
- ✓30k requests / mo
- ✓3 API keys
- ✓All core checks
- ✓Customize detection rules
- ✓Email support
Silver
For a product going to production.
- ✓100k requests / mo
- ✓10 API keys
- ✓Audit logs
- ✓Customize detection rules
- ✓Priority email support
Gold
Scale with custom protection.
- ✓750k requests / mo
- ✓25 API keys
- ✓Customize detection rules
- ✓Priority support
Enterprise
On your terms, on your infra.
- ✓Unlimited requests
- ✓Unlimited API keys
- ✓On-prem / VPC deploy
- ✓SLA & SSO
- ✓Dedicated support
Ship safer AI in minutes
Drop AgentGuards in front of your model or wire it into your coding agent via MCP.