Add OmniRoute — self-hostable AI gateway with 4-tier fallback

[diegosouzapw]

Add OmniRoute

OmniRoute is a self-hostable AI gateway with:

• 🔄 4-tier cascading fallback — automatic retry across providers
• ⚖️ Multi-provider load balancing — distribute requests across OpenAI, Anthropic, Google, local models
• 🔌 OpenAI-compatible API — drop-in replacement, works with any OpenAI SDK
• 🎯 200+ models supported — GPT, Claude, Gemini, Llama, Mistral, etc.
• 🐳 Docker-ready — single docker compose up deployment
• 📊 Dashboard — real-time monitoring, flow visualization, provider management

GitHub: https://github.com/diegosouzapw/OmniRoute
License: MIT

[Copilot]

Pull request overview

This pull request adds OmniRoute to the README's LLM Inference section. OmniRoute is a self-hostable AI gateway that provides multi-provider routing, fallback mechanisms, and load balancing across 200+ AI models with an OpenAI-compatible API.

Changes:

• Added OmniRoute entry to the LLM Inference section with a description highlighting its gateway capabilities, fallback mechanisms, and model support

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

OmniRoute appears to be a gateway/routing tool rather than a direct inference engine. Similar tools like "AI Gateway" (Portkey) and "TensorZero" are listed in the "LLM Applications" section (lines 510, 551), while the "LLM Inference" section primarily contains tools that perform actual inference (vLLM, llama.cpp, ollama, TGI, TensorRT-LLM). Consider moving this entry to the "LLM Applications" section, or to the "other deployment tools" subsection within "LLM Inference" (after line 461) where similar routing/serving tools like FastChat are located.