Neil Stoker's starred repositories

LibreChat

Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development

Language:TypeScriptLicense:MITStargazers:14551Issues:107Issues:983

tortoise-tts

A multi-voice TTS system trained with an emphasis on quality

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:12269Issues:166Issues:497

Scrapegraph-ai

Python scraper based on AI

Language:PythonLicense:MITStargazers:12181Issues:82Issues:155

surya

OCR, layout analysis, reading order, line detection in 90+ languages

Language:PythonLicense:GPL-3.0Stargazers:8853Issues:74Issues:90

CopilotKit

A framework for building custom AI Copilots 🤖 in-app AI chatbots, in-app AI Agents, & AI-powered Textareas.

Language:TypeScriptLicense:MITStargazers:7367Issues:61Issues:91

outlines

Structured Text Generation

Language:PythonLicense:Apache-2.0Stargazers:6816Issues:45Issues:491

piper

A fast, local neural text to speech system

Language:C++License:MITStargazers:4850Issues:67Issues:396

moondream

tiny vision language model

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:4390Issues:51Issues:91

porcupine

On-device wake word detection powered by deep learning

Language:PythonLicense:Apache-2.0Stargazers:3570Issues:63Issues:537

pipecat

Open Source framework for voice and multimodal conversational AI

Language:PythonLicense:BSD-2-ClauseStargazers:1651Issues:19Issues:29

tarsier

Vision utilities for web interaction agents 👀

Language:Jupyter NotebookLicense:MITStargazers:1221Issues:7Issues:14

RealtimeSTT

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Language:PythonLicense:MITStargazers:1163Issues:20Issues:43

distributed-llama

Tensor parallelism is all you need. Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.

Language:C++License:MITStargazers:1001Issues:18Issues:36

GPT-4V-Act

AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

sqlite-vec

Work-in-progress vector search SQLite extension that runs anywhere.

Language:CLicense:Apache-2.0Stargazers:837Issues:39Issues:27

page-assist

Use your locally running AI models to assist you in your web browsing

Language:TypeScriptLicense:MITStargazers:815Issues:9Issues:79

Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"

Language:PythonLicense:MITStargazers:688Issues:27Issues:39

openWakeWord

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:523Issues:12Issues:107

vad

Voice activity detector (VAD) for the browser with a simple API

Language:TypeScriptLicense:NOASSERTIONStargazers:477Issues:11Issues:77

paddler

Stateful load balancer custom-tailored for llama.cpp

Language:GoLicense:MITStargazers:372Issues:4Issues:2

cq2

Document. Discuss. Decide.

Language:TypeScriptLicense:AGPL-3.0Stargazers:289Issues:6Issues:0

Linguflex

Command Your World with Voice

Language:PythonLicense:MITStargazers:237Issues:9Issues:6

gemini-spatial-example

How to use bounding boxes with the Gemini API

Language:CLicense:Apache-2.0Stargazers:63Issues:0Issues:0

Building-LLM-Powered-Applications

Building Large Language Model Applications, Published by Packt

Language:Jupyter NotebookLicense:MITStargazers:62Issues:0Issues:0

TurnGPT

TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog

Language:PythonLicense:MITStargazers:36Issues:3Issues:1

lambda-bedrock-s3-streaming-rag

Fully serverless streaming RAG application

Language:JavaScriptLicense:MIT-0Stargazers:24Issues:0Issues:0

stream2sentence

Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.

datasets_turntaking

Datasets for turn-taking research

Language:PythonStargazers:10Issues:2Issues:0
Language:JavaScriptLicense:Apache-2.0Stargazers:2Issues:1Issues:0