NeuralTrust
Documentation
NeuralTrust is the runtime and red-team platform for AI and agent workflows. Enforce security policies at every surface your users interact with — gateway, browser, API, and endpoint — and stress-test your models before shipping them. This site is the reference for all of it. More atneuraltrust.ai.
Products
Pick the area you’re working in.
Runtime by TrustGate
Runtime security for LLM and agent traffic across four enforcement
surfaces: Gateway, Browser, API, and Endpoint.
AI Threat Detection
Red team LLM applications, build evaluations, and measure safety
and reliability before production rollout.
Get started
End-to-end walkthroughs for the three most common first journeys.
Your first Gateway
Stand up a TrustGate Gateway, create a route, and send your first
protected request to an LLM upstream.
Your first red team
Connect an application, run a jailbreak and prompt-injection test
suite, and review the results.
Provision a data plane
Deploy TrustGate inside your own AWS, GCP, or Azure account for a
hybrid setup.
Administer the platform
Tenant administration and infrastructure shared across products.
Platform settings
Users, SSO, SCIM, audit logs, SIEM, custom domain, data plane, and
feature flags — the tenant-wide controls for your team.
Architecture & deployment
Control plane, data plane, and deployment modes (SaaS, hybrid, and
self-hosted) that make up NeuralTrust.
Reference
Core concepts and API material.
Enforcement surfaces
How Gateway, Browser, API, and Endpoint compare — and when to layer
them for defense-in-depth.
API reference
Endpoints for TrustGate administration, routes, API keys, and
runtime actions.