Skip to main content

NeuralTrust

Documentation

NeuralTrust provides security controls for AI applications and agents. Use TrustGate to route and govern model traffic, TrustGuard to inspect it at runtime, and TrustTest to evaluate models before deployment. This documentation covers configuration and operation.

Products

Documentation by product.

TrustGate

Route LLM and MCP traffic across providers, with authentication, load balancing, and policy controls.

TrustGuard

Inspect prompts, responses, and tool activity at runtime, then monitor, block, or redact according to policy.

TrustTest

Test LLM applications against adversarial scenarios and evaluate their safety and reliability before deployment.

Get started

Follow a guided setup for each product.

Create a gateway

Create a TrustGate gateway, register a provider, and send a request through it.

Connect TrustGuard

Attach runtime security to your gateway and inspect prompts and responses inline for jailbreaks, PII, and tool abuse.

Run a red-team evaluation

Connect an application, run a jailbreak and prompt-injection test suite, and review the results.

Integrations

Connect NeuralTrust to tools already in your AI stack.

Browse integrations

Find setup guides for coding agents, agent frameworks, AI gateways, applications, and edge platforms.

Coverage

Compare monitoring, blocking, redaction, and approval support for model traffic and tool calls.

Administer the platform

Tenant administration and infrastructure shared across products.

Platform settings

Manage users, SSO, SCIM, audit logs, SIEM, custom domains, data planes, and feature flags.

Architecture & deployment

Review the control-plane and data-plane architecture, including SaaS and Hybrid deployment modes.

Reference

Console workflows, concepts, and the control-plane API.

TrustGate concepts

Learn how gateways, registries, consumers, authentication, policies, and roles work.

API

Automate the same control-plane resources available in the console.