OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

Http client base pydantic, with requests, aiohttp and httpx

Comprehensive Guide Running Kuzco Inference Training LLM Models AI w/ CPU & Docker - Commit Deployment

Ollama-compatible API proxy server with Chutes.ai's LLM services.

🔗 Simplify API interactions with this OpenAI-compatible proxy designed for seamless integration in Python projects.

API Backend of my submission for the CapitalOne Yelp Challenge

Minimal, stateless AI service proxy for Gemini and other LLMs

Primer hito del proxy HTTP seguro para usar APIs internas/abiertas dentro de la red agregando autenticación Bearer. Actúa como “drop-in” delante de servicios existentes: reenvía cualquier ruta al destino, preserva headers/cuerpo, soporta streaming y expone endpoints de salud y métricas.

AI API proxy with budget control