Back to browse
GitHub Repository

A lightweight AI gateway that makes LLM providers OpenAI-compatible.

11 starsTypeScript

Lightport – AI gateway that makes LLM providers OpenAI-compatible

by smokybay·Apr 27, 2026·1 point·0 comments

AI Analysis

●●SolidShip ItSolve My Problem

Stripped-down Portkey fork handling protocol translation for 77 providers without enterprise bloat.

Strengths
  • Integration tests for 77 providers ensure compatibility rather than mere claims.
  • Deliberate scope reduction removes caching, retries to minimize maintenance surface.
  • Powers Glama.ai in production, proving it is not just a hobby fork.
Weaknesses
  • LiteLLM already dominates this space with more features and broader adoption.
  • No builtin retry logic or caching means you must build those layers.
Target Audience

Backend developers building AI apps who need provider abstraction

Similar To

LiteLLM · Portkey AI Gateway · Helicone

Post Description

I am making Lightport open-source – the AI gateway that's been powering Glama.

GitHub: https://github.com/glama-ai/lightport

Live: https://glama.ai/ai/gateway

Why?

We're going all-in on the MCP ecosystem – it's what we're best at. Open-sourcing the gateway is both a thank-you to the community that helped us grow and a way to keep us focused.

The short backstory:

Lightport began as a fork of Portkey. We needed a way to make various LLM providers OpenAI-compatible, and Portkey provided a solid foundation. But it also came with many higher-level features (guardrails, billing, etc.) that we didn't think belonged at this layer – and that made it hard to iterate on provider compatibility. So we slimmed it down, fixed bugs, added integration tests for 80+ providers, and shaped it into one thing: a reliable, lightweight layer that makes any LLM provider OpenAI-compatible.

What's next:

More modules will follow – guardrails, billing, retries, telemetry – each open-sourced as standalone middleware. We'll continue to maintain Lightport in the open, with a focus on OpenAI compatibility across LLM providers.

For Glama users:

The Glama AI gateway will continue to function as a privacy-first gateway, but we will support only a curated set of providers (OpenAI, Anthropic, Google, Grok, Groq, DeepSeek, Alibaba, Moonshot, and a few others). For everything else, OpenRouter is a great alternative.

Try it, break it, build with it. I can't wait to see what you make.

Similar Projects