- United States
- sethm.me
- in/sethmillerp
- https://litmod.app
Highlights
- Pro
Stars
Zero-dependency local text-to-speech CLI. Wraps Chatterbox ONNX models in a standalone Rust binary for macOS, Linux, and Windows.
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale…
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
An open-source AI agent that brings the power of Gemini directly into your terminal.
LLM Frontend for Power Users.
Laptop Internal Keyboard Enable/Disable Script
Provides Piper neural text-to-speech voices as a browser extension
Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allow…
EntityDB is an in-browser vector database wrapping indexedDB and Transformers.js over WebAssembly
Repository for YouTube tutorial on how to backup a Supabase DB for free and then restore that backup
A complete starter kit that you can use to build and deploy a Next.js SaaS app powered by Paddle Billing.
A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone a…
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A lightweight 3D physics engine written in JavaScript.
Beautiful 3D dice roller built for Owlbear Rodeo
The best 3D dice roller for web stuff.
A modified implementation of Anton Natarov's 3D dice roller
A town generator that is suitable for out of the box play in any fantasy TTRPG setting.
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input