llm-router

Access models from OpenAI, Groq, local Ollama, and other providers by setting LLM-router as the base URL in Cursor.

LLM-router is a reverse proxy that routes chat/completions API requests to various OpenAI-compatible backends based on the model's prefix.

Cursor lacks support for local models and the flexibility to switch between multiple LLM providers efficiently. There's clear demand in the community, evidenced by months of unanswered requests for such features on Cursor's GitHub and Discord channels.

• The Override OpenAI Base URL setting requires a URL that is publicly accessible and secured with https, complicating the use of local models.
• The platform allows configuration for only one LLM provider at a time, which makes it cumbersome to switch between service providers.
• Create your configuration file
• A sample configuration file config-sample.json is provided in the repository
• Either rename this file to config.json or create a new config.json file using the example below
• This file defines which LLM backends are available and how to route to them
• Launch LLM-router to manage API requests across multiple backends
• If you haven't set a LLMROUTERAPIKEY environment variable, the program will generate a random strong API key