AI product Open source

OmniRoute

OmniRoute is an open-source, self-hosted AI gateway developed by diegosouzapw. It exposes model providers through a single OpenAI-compatible endpoint and routes requests according to provider availability, quotas, cost, and latency, with automatic fallback and model chaining. The gateway is designed for local-first operation, keeping provider keys locally and supporting encrypted key storage.

View repository Visit site Mentioned in 3 videos ↓

Overview

Its documented features include quota-aware scheduling, context compression through the RTK and Caveman mechanisms, and integrations for MCP and A2A workflows. The repository describes compatibility with coding clients such as Claude Code, Codex, Cursor, OpenCode, Cline, and Copilot, along with desktop and progressive web app interfaces. It is distributed under the MIT license and supports hundreds of providers and more than a thousand model identifiers.

What OmniRoute is used for

3 uses taken from transcripts — each links to the moment in the video.

  • An open-source local AI gateway that provides one endpoint for hundreds of model providers. It routes requests across providers, supports fallback and model chaining, and keeps keys encrypted locally.

  • An open-source, self-hosted AI gateway that places many model providers behind one OpenAI-compatible endpoint. It routes requests based on cost, latency, quota, and provider availability while keeping keys local.

  • An open-source AI gateway that exposes many providers and models through one OpenAI-compatible endpoint. It routes requests across providers with quota-aware automatic fallback, context compression, encrypted keys, and local-first operation.

Videos mentioning OmniRoute

3 in the library.