Open Source AI Gateways Software
AI Gateways software provides a unified interface to manage requests between applications and multiple large language model providers. These tools handle API routing, load balancing, and traffic orchestration to prevent service interruptions. This type of software is for developers who need to monitor token usage and track costs across different AI accounts. Self-hosting these apps allows you to keep API keys and prompt histories on your own infrastructure. This setup ensures that model routing and governance policies remain private and independent of any single provider.
This page lists 10 open source tools in the AI Gateways category. The most popular are Pi, LocalAI and Kong. Most use the MIT or Apache-2.0 license, and 9 offer an official Docker image.
Pi
A terminal based coding agent with multi provider LLM support and a TypeScript extension system.
LocalAI
An open-source AI engine for running LLMs, vision, voice, image, and video models on local hardware.
Kong
A cloud native API and AI gateway for managing traffic, routing, and LLM orchestration.
Portkey AI Gateway
Route requests to over 1,600 language, vision, audio, and image models through a unified API interface.
Manifest
A smart model router that connects AI agents to multiple providers through a single OpenAI-compatible endpoint.
Bifrost
Unify access to multiple AI providers through a single OpenAI compatible API with built in governance.
Helicone
Log, monitor, and debug large language model applications with a unified gateway for AI model routing.
AntigravityManager
Manage multiple Google Gemini and Claude AI accounts with automated switching and real-time quota monitoring.
Envoy AI Gateway
A gateway for routing application traffic to generative AI services with support for over sixteen LLM providers.
LLM Gateway
Route and manage requests across multiple LLM providers using a single API with built-in usage analytics.
Join our newsletter to get shiny new open source software delivered to your inbox. Unsubscribe anytime.