Manifest LLM Gateway
An open-source, self-healing LLM gateway that connects agents and apps to 300+ models through one OpenAI-compatible endpoint, with automatic fallback on failed requests.
Manifest LLM Gateway is an open-source LLM gateway for AI agents and apps. It connects a user's API keys, subscriptions and local models to a single OpenAI-compatible endpoint, routing each query to the right model so no application is locked into one provider.
It offers custom routing across API keys, subscriptions, local models and custom providers, full request and response body logging for successes and errors, cost tracking with notifications and limits, and automatic fallback to a different model when a query fails. It connects to more than 300 models through 35 built-in provider connections plus any custom OpenAI- or Anthropic-compatible endpoint, discovering provider catalogs dynamically as credentials are connected, and a request can specify an "auto" model to let Manifest choose.
It runs as a cloud-hosted service or self-hosted as a Docker image, with deployment guides for platforms including Railway, Render, DigitalOcean, AWS, GCP, Fly.io, Coolify, Easypanel, Heroku, Koyeb and Apple Containers, backed by durable request-recording storage on every deployment path.