Run LiteLLM in a multi-worker setup on the Web with Pyodide
The Pyodide JavaScript package
n8n community node for OpenAI with LiteLLM prompt caching support
JS Implementation of LiteLLM
The Pyodide JavaScript package
[](https://github.com/alexmojaki/pyodide-worker-runner/blob/master/LICENSE) [ as an npm package.
PyScript
<a href="https://github.com/suren-atoyan/x-python/" target="_blank" rel="noreferrer"> <img align="center" width="30%" height="auto" src="./playground/logo.svg" style="margin-bottom: 10px"> </a>
Xyne CLI - A powerful AI assistant in your terminal with file operations, bash mode, drag-and-drop support, and multi-provider AI integration
OpenCode plugin for LiteLLM proxy support with auto-detection and dynamic model discovery
This project integrates JupyterLite with the Pyodide kernel and custom extensions such as `jl-galaxy`.
LiteLLM auto-generated type-safe API client
OpenCode plugin that displays which model was selected by a LiteLLM auto router (complexity router, semantic router, etc.)
OpenCode plugin for any LiteLLM proxy — auto-discovers models, auth, and capabilities
Custom n8n node to connect with LiteLLM embeddings API
Patched OpenAI Codex CLI with first-class LiteLLM support
LiteLLM integration for Pi — dynamic model sync, accurate cost tracking, and session grouping
Pi extension that discovers models from a LiteLLM gateway and registers them as a provider.
n8n community node for LiteLLM — connect any LLM provider via a LiteLLM proxy using a simple JSON options field
Typescript client for the Hugging Face Inference Providers and Inference Endpoints