Gabor Barany (gbarany)

gbarany

Geek Repo

Location:London

Github PK Tool:Github PK Tool

Gabor Barany's starred repositories

anything-llm

The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.

Language:JavaScriptLicense:MITStargazers:16730Issues:136Issues:1176

twenty

Building a modern alternative to Salesforce, powered by the community.

Language:TypeScriptLicense:AGPL-3.0Stargazers:14966Issues:75Issues:2750

marker

Convert PDF to markdown quickly with high accuracy

Language:PythonLicense:GPL-3.0Stargazers:13823Issues:57Issues:155

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

Language:PythonLicense:MITStargazers:13010Issues:107Issues:264

nocobase

NocoBase is a scalability-first, open-source no-code/low-code platform for building business applications and enterprise solutions.

Language:TypeScriptLicense:NOASSERTIONStargazers:10954Issues:123Issues:826

faster-whisper

Faster Whisper transcription with CTranslate2

Language:PythonLicense:MITStargazers:10061Issues:120Issues:599

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Language:PythonLicense:BSD-4-ClauseStargazers:9938Issues:123Issues:640

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Language:PythonLicense:Apache-2.0Stargazers:8128Issues:81Issues:672

social-app

The Bluesky Social application for Web, iOS, and Android

Language:TypeScriptLicense:MITStargazers:7155Issues:67Issues:1641

awesome-software-architecture

πŸš€ A curated list of awesome articles, videos, and other resources to learn and practice software architecture, patterns, and principles.

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Language:TypeScriptLicense:Apache-2.0Stargazers:5580Issues:32Issues:71

skyvern

Automate browser-based workflows with LLMs and Computer Vision

Language:PythonLicense:AGPL-3.0Stargazers:5389Issues:36Issues:70

LaVague

Large Action Model framework to develop AI Web Agents

Language:PythonLicense:Apache-2.0Stargazers:4946Issues:49Issues:195

cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

Language:PythonLicense:Apache-2.0Stargazers:2968Issues:32Issues:20

portfolio

Track and evaluate the performance of your investment portfolio across stocks, cryptocurrencies, and other assets.

Language:JavaLicense:EPL-1.0Stargazers:2753Issues:70Issues:1889

vocode-core

πŸ€– Build voice-based LLM agents. Modular + open source.

Language:PythonLicense:MITStargazers:2500Issues:43Issues:142
Language:PythonLicense:Apache-2.0Stargazers:2439Issues:31Issues:21

whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Language:Jupyter NotebookLicense:BSD-2-ClauseStargazers:2407Issues:45Issues:150

whisper-asr-webservice

OpenAI Whisper ASR Webservice API

Language:PythonLicense:MITStargazers:1844Issues:27Issues:145

langchain-nextjs-template

LangChain + Next.js starter template

Language:TypeScriptLicense:MITStargazers:1226Issues:12Issues:27

crawl4ai

πŸ”₯πŸ•·οΈ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

Language:PythonLicense:Apache-2.0Stargazers:1211Issues:15Issues:25

ml-4m

4M: Massively Multimodal Masked Modeling

Language:PythonLicense:Apache-2.0Stargazers:1192Issues:29Issues:10

dbxcli

A command line client for Dropbox built using the Go SDK

Language:GoLicense:NOASSERTIONStargazers:1037Issues:37Issues:139

vision-agent

Vision agent

Language:PythonLicense:Apache-2.0Stargazers:862Issues:12Issues:5

agents

Build real-time multimodal AI applications πŸ€–πŸŽ™οΈπŸ“Ή

Language:PythonLicense:Apache-2.0Stargazers:637Issues:24Issues:74

shadcn-minimal-tiptap

Minimal Tiptap Editor

Language:TypeScriptLicense:MITStargazers:287Issues:2Issues:4

financial-agent-ui

Financial agent + generative UI

Language:TypeScriptStargazers:221Issues:3Issues:0

BentoChain

A voice-enabled chatbot application built using of πŸ¦œοΈπŸ”— LangChain, text-to-speech, and speech-to-text models from πŸ€— Hugging Face, and 🍱 BentoML.

docker-whisperX

Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)

Language:DockerfileLicense:MITStargazers:99Issues:5Issues:14

llama-farm-chat

Use locally-hosted LLMs to power your cloud-hosted webapp

Language:TypeScriptLicense:Apache-2.0Stargazers:27Issues:3Issues:0