Back to directory

Occludra

A self-hosted proxy that sits between an application and any LLM provider, redacting personal data and secrets and blocking prompt-injection attempts before a request reaches the model.

Occludra

Occludra is a self-hosted AI security gateway that sits between an application and any LLM provider, scanning every request for sensitive data and attacks before forwarding it. It redacts emails, phone numbers, credit card numbers, government ID numbers and API keys, and blocks detected prompt-injection and jailbreak attempts, failing closed if the safety layer goes down.

It exposes an OpenAI-compatible endpoint so an existing integration can switch providers by changing one line, and routes to eight providers including OpenAI, Anthropic, Groq and Ollama. It runs entirely on the user's own machine through Docker with no telemetry, and a paid cloud tier adds SSO, role-based access control and SIEM connectors. It is written in Python and Apache-2.0 licensed.

More in LLM gateways

See all 106
  • aihappey-ai

    github.com

    A stateless, multi-provider .NET AI gateway exposing normalized OpenAI- and Anthropic-compatible endpoints, managed agents and skills across a very large catalog of models.

  • Unified AI System

    happy520ai.github.io

    A self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A, turning a rough request into a structured, reviewable prompt before it runs.

  • Subroute

    github.com

    A local AI gateway and desktop control desk that gives coding tools one steady endpoint, so switching between AI subscriptions, API providers and local models doesn't mean reconfiguring every client.