KenyonY/openai-forward
An API reverse proxy and forwarding service for OpenAI-compatible LLM endpoints with rate limiting, token pacing, and predictive caching.

Velocity · 7d
+0.8
★ / day
Trend
→steady
star history
OpenAI-Forward is a forwarding service for large language models acting as an OpenAI API reverse proxy. It provides rate control at both request and token levels, intelligent caching for predicted responses, API key management, and conversation logging. It can proxy requests to local models (such as LocalAI) or cloud-based LLM endpoints, serving as infrastructure for deploying and scaling LLM applications.