Skip to main content

Rivaro Developer Documentation

Rivaro is an AI runtime enforcement proxy. It sits between your AI application and the AI provider, scanning every request and response for violations and enforcing your security policies — transparently.

For Developers​

Start here if you're integrating Rivaro into your AI application.

Getting Started​

Your first request through the proxy in 5 minutes. Covers SDK configuration, detection keys, and a working example.

Provider Guides​

Detailed integration for each supported AI provider — SDK configuration, supported endpoints, streaming, tool/function calling, and examples.

  • OpenAI — GPT-4, embeddings, audio, function calling
  • Anthropic — Claude, tool use, streaming
  • Azure OpenAI — Deployments, api-key auth
  • AWS Bedrock — InvokeModel, Converse, SigV4 auth
  • Vertex AI — Gemini, GCP project paths, Bearer token

Error Handling​

How to handle Rivaro-specific errors (401, 403, 429, 451), distinguish them from provider errors, implement retry strategies, and debug enforcement decisions.

For Administrators​

Start here if you're setting up Rivaro for your development team.

Configuration Guide​

Set up AppContexts (provider routing), create detection keys, configure rate limits and allowed models, and manage organization settings.

Enforcement & Policies​

Configure what happens when violations are detected. Covers observation mode vs enforcement, policy actions (block, redact, log), rule matching, and agent governance (trust scores, quarantine, termination).

Reference​

These pages are useful for both developers and administrators.

Understanding Detections​

Complete reference for everything Rivaro detects: 7 risk domains, 15 risk categories, 60+ detection types, severity levels, lifecycle stages, and data classifications.

API Reference​

Full OpenAPI specification for all proxy endpoints — every supported provider path, request/response formats, authentication, and error responses.

I want to…Go to
Make my first proxy requestGetting Started
Integrate OpenAI through RivaroOpenAI Guide
Integrate Anthropic through RivaroAnthropic Guide
Set up detection keys for my teamConfiguration Guide
Configure enforcement policiesEnforcement & Policies
Understand why a request was blockedError Handling
See what Rivaro can detectUnderstanding Detections
Look up a specific endpointAPI Reference