 |
VOOZH | about |
|
VOOZH | about |
Provide observability and gateway control for Agent-to-Agent (A2A) protocol traffic, supporting both JSON-RPC and REST bindings
Use AWS Guardrails to validate requests and/or responses in the AI Proxy plugin before forwarding them between clients and upstream LLMs.
Use Azure AI Content Safety to check and audit AI Proxy plugin messages before proxying them to an upstream LLM
Use a third-party guardrails service to validate requests and/or responses in the AI Proxy plugin before forwarding them between clients and upstream LLMs
Audit and validate LLM prompts with Google Cloud Model Armor before forwarding them to an upstream LLM.
Evaluate and optimize your Large Language Models with accuracy
Inspect and enforce Lakera Guard safety policies on LLM requests and responses before they reach upstream models.
Convert APIs into MCP tools, proxy MCP servers, expose multiple MCP tools for AI clients, and observe MCP traffic in real time.
Protect sensitive information in client request or response bodies before they reach upstream services or clients
Compress prompts before they are sent to LLMs to reduce costs, and improve latency
Prepend or append an array of llm/v1/chat messages to a user’s chat history
Check text completion requests against a list of allowed or denied expressions
The AI Proxy plugin lets you transform and proxy requests to a number of AI providers and models.
The AI Proxy Advanced plugin lets you transform and proxy requests to multiple AI providers and models at the same time. This lets you set up load balancing between targets.
Create RAG pipelines by automatically injecting content from a vector database
Use an LLM service to transform a client request body prior to proxying the request to the upstream server
Use an LLM service to transform the upstream HTTP(S) prior to forwarding it to the client
Enhance performance for AI providers by caching LLM responses semantically
Semantically and intelligently create allow and deny lists of topics that can be requested across every LLM.
Permit or block prompts based on semantic similarity to known LLM responses, preventing misuse of llm/v1/chat or llm/v1/completions requests
Authenticate clients with mTLS certificates passed in headers by a WAF or load balancer
Secure Kong with username and password protection, use LDAP search and service directory mapping
Secure routes and services with client certificate and mutual TLS authentication
Integrate Kong Gateway with a third-party OAuth 2.0 Authorization Server
Integrate Kong Gateway with a third-party OpenID Connect provider
Provides SAML v2.0 authentication and authorization between a service provider (Kong) and an identity provider (IdP)
Configure Kong Gateway to obtain an OAuth2 token to consume an upstream API
Publish request and response logs to a Solace endpoint or topic
A licensed add-on through Konnect Metering & Billing. Meter API requests and AI token usage for usage-based billing. Supports flexible customer identification, custom pricing dimensions, and fine-grained traffic filtering.
The CORS plugin lets you add Cross-Origin Resource Sharing (CORS) to a Service or a Route.
Detect and block injection attacks using regular expressions
Apply size checks on JSON payload and minimize risk of content-level attacks
Proxies TLS client certificate metadata to upstream services via an HTTP headers
The ACE plugin manages developer access control to APIs published with Dev Portal.
Consume messages from Confluent Cloud Kafka topics and make them available through HTTP endpoints
Allows Kong Gateway to connect to intermediary transparent HTTP proxies
Cache and serve commonly requested responses in Kong Gateway
Consume messages from Kafka topics and make them available through HTTP endpoints
Validate HTTP requests and responses based on an OpenAPI 3.0 or Swagger API Specification
Cache and serve commonly requested responses in Kong, in-memory or using Redis
You can use the Rate Limiting plugin to limit how many HTTP requests can be made in a given period of seconds, minutes, hours, days, months, or years.
Enhanced rate limiting capabilities such as sliding window support, Redis Sentinel support, and increased performance
Prevent abuse and protect services with absolute limits on the number of requests reaching the service
Consume messages from Solace topics and make them available through HTTP endpoints
Validate that incoming webhooks adhere to the Standard Webhooks specification
Set custom timeouts on connections to upstream services to override Gateway Service-level timeouts.
Block incoming WebSocket messages greater than a specified size
Transform requests into Kafka messages in a Confluent Kafka topic.
Insert arbitrary API calls before proxying a request to the upstream service.
Use powerful regular expressions, variables, and templates to transform API requests
Modify the upstream response before returning it to the client, with greater customization capabilities
Transform routing by changing the upstream server, port, or path
Transform requests into Solace messages in a Solace queue or topic
Transform JSON objects included in API requests or responses using jq programs
API security with inline request blocking and data capture
Sign requests with AWS SIGV4 and temp credentials for secure use of AWS Lambdas in Kong
Inspect AI prompts against CrowdStrike Falcon AIDR input rules, blocking threats before they reach the upstream LLM
Inspect LLM responses against CrowdStrike Falcon AIDR output rules, redacting or blocking sensitive content before delivery to the client
Detect and mitigate attacks on mobile apps, websites, and APIs with DataDome bot and online fraud protection
Integrate Kong Gateway with Imperva API Security to discover, monitor, and protect APIs
Integrate Impart Security’s WAF and API security protection platform with Kong Gateway.
Integrate Kong API Gateway with Inigo GraphQL Observability and Security
Block responses with bodies greater than a specified size
Mock virtual API request and response pairs through Kong Gateway
Expose OAS/Swagger/etc. specifications of auth protected APIs proxied by Kong
Powerful API analytics and usage-based billing to monetize APIs
AI-DR runtime protection for all OpenAI-compliant modules through your Kong AI Gateway
Noname Security machine learning & prevention blocking for Kong Gateway discovery
Enhance your API security by integrating your Kong Gateway with Cortex API Security
Real-time security scanning for AI/LLM traffic using PAN Prisma AI Runtime Security
Integrate Kong API Gateway with Salt Security Discovery & Prevention for API-based apps
Strengthen your overall API Security with TrendAI Vision One
Wallarm is AI-Powered Security Platform for protecting microservices and APIs
