Matt Hoffner's repositories
backseat-pilot
Bring your own copilot server and customize commands to refactor instead of autofill or tabbed completion.
web-llm-embed
Document chat using Web LLM and Transformers.js embeddings
neo-voice-link
Proof of concept voice assistant using Twilio's telephony, Deepgram for transcription, OpenAI GPT models, and ElevenLabs' text-to-speech technology.
codetree-ai
LLM chat directly into a WebAssembly powered javascript live editor and preview
esbuild-function
esbuild-function is an in-browser compiler for JavaScript, TypeScript, and JSX, enhancing Large Language Models (LLMs) with real-time code execution and analysis.
react-evergreen
A Threads web clone with latest React
audiocraft-tools
Collection of tools for using AudioCraft
audiocraft_plus
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
dishcovery-eats
Web app for discovering restaurants. Experimenting with LLM functions.
google-openai-ui
A Google clone with OpenAI functions
llama-use-chat
Example using Llama.cpp with useChat hook
ChatLLM-Web
🗣️ Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server.Powered by web llm
edge-chat
Experimenting with LLM chat with client side embeddings using Web Workers and IndexedDB
graphql-to-openapi
Convert a graphql query + graphql schema into an openapi spec.
jsonformerjs
Javascript version of jsonformer
llama-cpp-python
Python bindings for llama.cpp
llava-cpp-server
LLaVA server (llama.cpp).
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
photo-chat
Upload an image which is converted to text using transformers.js. The output is used as an input to an interactive chatbot.
react-llm
Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. Just useLLM().