AI
All About AI
Back to stack index

Language

Go

Common for inference CLIs and high-throughput proxies.

Official site

Directory projects (3)

  • Ollama

    Simple CLI and API for pulling and serving open models on your machine.

  • LiteLLM

    OpenAI-compatible proxy that unifies dozens of model providers behind one key.

  • Helicone

    Logging proxy that surfaces cost, latency, and error rates per route.