A lightweight LiteLLM server boilerplate pre-configured with uv and Docker for hosting your own OpenAI- and Anthropic-compatible endpoints. Includes LibreChat as an optional web UI.

A LiteLLM proxy server with built-in message sanitization for Mistral models

High-performance, async-first system that computes and monitors LLM API spend across millions of requests with PostgreSQL and Prometheus.

Adds LiteLLM as a provider within Copilot in VSCode, expanding the models you can access significantly. Available on Visual Studio Code Marketplace: https://marketplace.visualstudio.com/items?itemName=Gethnet.litellm-connector-copilot

A VSCode extension to use LiteLLM Provider in Copilot Chat

Compact LLMOps stack for production-grade LLM apps: LiteLLM proxy + Langfuse observability. Self-hostable, scalable, open-source toolkit for AI engineers