Production AI Guardrails

Security for every LLM call.

LLM Shield sits between your application and your LLM. Inspects inputs, enforces policies, scans outputs, and secures agentic tool-calling workflows — with per-tenant isolation, runtime audit, and compliance mappings out of the box.

19
Guardrails
13
Industry suites
~26K
Red-team prompts
<250ms
Inspection budget

Why LLM Shield

🛡️

Defense in depth

19 guardrails across input safety, output quality, and agentic security — composed into a two-tier parallel pipeline.

🏢

Built for multi-tenant

Per-tenant policies, rate limits, quotas, and audit logs persisted in Redis. Drop-in for SaaS or enterprise.

Fast where it matters

CPU guardrails run first under a 250ms budget. LLM-based checks fire only when needed.

🤖

Agent-native security

Role-based tool authorization, MCP server validation, data taint tracking, and goal-drift detection.

📋

Compliance-ready

Mappings for NIST AI RMF, OWASP LLM Top 10, and ISO 42001 — ship audits, not spreadsheets.

🔌

Framework agnostic

LangChain, CrewAI, OpenAI SDK, Anthropic, or a plain OpenAI-compatible HTTP gateway — wire it in once.

Where to start

If you want to… Go to
Spin it up in 5 minutes Quickstart
Understand how it answers common buyer questions FAQ
See every endpoint API Reference
Pick the right deployment shape Installation Guide
Run on-prem with HA On-Premises Deployment
Wire up agents (LangChain / CrewAI / OpenAI) Agentic Integration
Use Shield in your IDE (Cursor / Claude / VS Code) Connect Shield to Your IDE
Use your existing IdP (Okta / Entra / Google) Identity Provider Interoperability
Add guardrails at your AI gateway (LiteLLM / Portkey / Kong) AI Gateway & Proxy Interoperability
Stop data leaking into web AI (ChatGPT / Gemini / Claude) Edge Fast-Path (Browser DLP)
Enforce MCP tool allowlists at runtime (not just client-side) MCP Runtime Enforcement
Plan an enterprise rollout / cover agents you didn’t build Enterprise Integration Architecture
Build a feature the right way (spec-first) Spec Template (how we build)
Map to NIST / OWASP / ISO controls Compliance Mapping

Where it runs

Managed cloud, self-hosted in your VPC, or fully on-prem / air-gapped — same APIs, same guardrails, same policies. Shield is a container you run wherever you need it; nothing is locked to a hosted control plane.

Model Runs on Guide
Cloud / managed RunPod, Cloud Run, Fly, Render Quickstart
Self-hosted (your VPC) your Kubernetes / VMs Installation Guide
On-prem / air-gapped RHEL + NVIDIA GPU, Docker Compose / K8s / OpenShift On-Premises Deployment

Two container images

  1. Full Shield (Dockerfile) — GPU worker with llama.cpp + all guardrails + admin portals
  2. Admin-only (Dockerfile.admin) — Lightweight (~150 MB) portal + tenant APIs, no GPU. Runs anywhere (Cloud Run, Fly, Render, laptop).

Both share the same backend APIs and connect to the same Redis for tenant state.

┌─────────────┐   ┌──────────────────┐   ┌─────────────────┐
│  Tenant App │──▶│  Full Shield     │──▶│  Redis (Upstash │
│  (your AI)  │   │  (GPU worker)    │   │  or local)      │
└─────────────┘   └──────────────────┘   └─────────────────┘
                                                 ▲
                  ┌──────────────────┐           │
                  │  Admin Portal    │───────────┘
                  │  (lightweight,   │  Per-tenant policies,
                  │   runs anywhere) │  rate limits, audit log
                  └──────────────────┘

License

MIT