Discover Plugins for our AI Gateway
Enrich and customize the NeuralTrust platform with easy to integrate plugins
Traffic Management
Plugins to manage your AI traffic more efficiently
Load Balancing
A dynamic load balancing plugin that evenly distributes traffic for optimal performance.
Built by NeuralTrust
Semantic Cache
Stores and retrieves responses based on semantic similarity, reducing latency and improving efficiency by reusing relevant answers from past interactions.
Built by NeuralTrust
Rate Limiting & Request Control
Plugins to enhance your AI with advanced control
Rate Limiter
Controls the number of requests sent to your AI models, preventing abuse, ensuring fair usage, and maintaining system performance.
Built by NeuralTrust
Request Size Limiter
Restricts the size of incoming requests to protect your AI systems from overload, ensuring stability and efficient resource usage.
Built by NeuralTrust
Content Security
Plugins to bring an extra layer of security to your AI
NeuralTrust Guardrail
Enhances safety by combining firewall rules and toxicity checks to block harmful, abusive, or policy-violating prompts before they reach your AI models.
Built by NeuralTrust
Contextual Security
Analyzes prompts in real time to detect context-specific risks, ensuring sensitive or harmful requests are identified before reaching your AI systems.
Built by NeuralTrust
AWS Bedrock Guardrail
Adds an extra layer of safety using AWS Bedrock Guardrails to filter harmful, toxic, or unwanted content before it reaches your AI models.
Built by NeuralTrust
OpenAI Toxicity Detection
Uses OpenAI’s moderation tools to identify and block toxic or harmful content, ensuring safer interactions with your AI models.
Built by NeuralTrust
Azure Toxicity Detection
Leverages Azure Content Moderation to detect and filter toxic, offensive, or inappropriate content before it reaches your AI models.
Built by NeuralTrust
Content Moderation
Sophisticated content filtering system designed to protect your AI gateway from potentially harmful or unwanted content.
Built by NeuralTrust
Application Security
Measures designed to protect against malicious input
CORS
Enforces Cross-Origin Resource Sharing (CORS) policies to control and secure how your AI Gateway resources are accessed from different origins.
Built by NeuralTrust
HTTP Security
Enforces security-related HTTP headers and validates incoming requests based on allowed hosts, HTTPS requirements, and security header policies.
Built by NeuralTrust
Injection Protection
Detects and blocks prompt injection attacks to prevent manipulation or unauthorized control of your AI models.
Built by NeuralTrust
Code Sanitation
Analyzes and cleans code prompts to remove potentially dangerous or malicious instructions before they are processed by your AI models.
Built by NeuralTrust
Data masking
Helps protect these sensitive details from exposure
Extending Functionality
TrustGate is designed with extensibility in mind
Observability and Monitoring
TrustGate provides comprehensive observability and monitoring capabilities
TrustLens
The TrustLens telemetry provider enables observability in TrustGate by sending trace-level data to the TrustLens platform.
Built by NeuralTrust
Prometheus
You can use this to collect metrics such as request throughput, latency distributions, and service health indicators.
Built by NeuralTrust
Create your own Plugin
Enhance your AI systems with powerful plugins that provide seamless scalability, comprehensive monitoring, and full compliance with global standards.
Get a demo