DeepSeek-OCR

This is the latest release from DeepSeek-AI. This project compresses long text into compact vision tokens literally turning paragraphs into pixels. It massively cuts token usage for LLMs while preserving accuracy when decoding back to text.

Creator:   deepseek-ai
Stars ⭐️:  6,200
Forked by:  270

Github Repo:
https://github.com/deepseek-ai/DeepSeek-OCR

#deepseek #ocr #opticalcompression
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

FileSync

FileSync is file sharing web application  that allows users to share files between multiple devices with end-to-end encryption in real time.

Creator:   polius
Stars ⭐️:  283
Forked by:  24

Github Repo:
https://github.com/polius/FileSync

#files #webapp
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

awesome‑game‑remakes

A list of open-source re-implementations of classic games (e.g., old PC/console noscripts). Fun if you like games, nostalgia or want to contribute by improving a remake.

Creator:   radek-sprta
Stars ⭐️:  1,100
Forked by:  38

Github Repo:
https://github.com/radek-sprta/awesome-game-remakes

#game #engine #opensource
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

gpt-engineer

gpt-engineer is a project in which you specify what you want in plain English and it iterates to produce a working codebase or scaffolded app. It’s an excellent playground for anyone exploring code-generation agents. And the repo contains clear install/usage instructions and a low-friction dev loop.

Creator:   AntonOsika
Stars ⭐️:  55,000
Forked by:  7,300

Github Repo:
https://github.com/AntonOsika/gpt-engineer

#codegeneration  #codingasssistant #ai
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

hexo

Hexo is a fast, Node.js-based blog framework that lets developers easily create static websites from Markdown files. It's designed for developers who prefer the command line and offers a rich plugin ecosystem for customization and flexible deployment.

Creator:   hexojs
Stars ⭐️:  41,000
Forked by:  5,000

Github Repo:
https://github.com/hexojs/hexo

#blog #nodejs
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

nightingale

Nightingale is an open-source monitoring system focused on simplifying alerting by providing an intuitive interface and integrated view of metrics, logs, and traces, aiming to be the "Grafana of Alerting."

Creator:   ccfos
Stars ⭐️:  13,000
Forked by:  2,000

Github Repo:
https://github.com/ccfos/nightingale

#grafana #monitoring
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

omi

Meet Omi, the world's largest open-source AI wearable that captures conversations, give summaries, action items and does actions for you. Simply connect Omi to your mobile device and enjoy automatic, high quality trannoscriptions of meetings, chats and voice memos wherever you are.

Creator:   BasedHardware
Stars ⭐️:  7,000
Forked by:  975

Github Repo:
https://github.com/BasedHardware/omi

#ai #wearable #opensource
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

WhisperLiveKit

Real-time & local speech-to-text translation and speaker diarization. With Server & Web UI.

Creator:   QuentinFuxa
Stars ⭐️:  8,000
Forked by:  729

Github Repo:
https://github.com/QuentinFuxa/WhisperLiveKit

#speechtotext #realtime
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

llama-fs

Tired of endlessly searching for that one file you know you saved somewhere? Llama-fs uses a local AI to understand your natural language and instantly find the files you're looking for, offering a smarter alternative to traditional file search. It indexes files and answers questions about their content, all while keeping data private on your machine.

Creator:   iyaja
Stars ⭐️:  6,000
Forked by:  371

Github Repo:
https://github.com/iyaja/llama-fs

#ai #files
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

social-analyzer

Social Analyzer is an API, CLI, and Web App for analyzing and finding a person's profile across +1000 social media or websites. This project is currently being used by some law enforcement agencies in countries where resources are limited.

Creator:  qeeqbox
Stars ⭐️:  17,000
Forked by: 1,500

Github Repo:
https://github.com/qeeqbox/social-analyzer

#socialmedia #analysis #detection
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

awesome-generative-ai-guide

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Creator:   aishwaryanr
Stars ⭐️:  19,500
Forked by:  4,000

Github Repo:
https://github.com/aishwaryanr/awesome-generative-ai-guide

#genai
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

MusicGPT

MusicGPT is an application that allows you to run the latest music generation AI models locally, in any platform and without using heavy dependencies like Python or machine learning frameworks.

Creator:  gabotechs
Stars ⭐️:  1,000
Forked by: 135

Github Repo:
https://github.com/gabotechs/MusicGPT

#music #LLM
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

vexa

Self-hosted, Multi-user API that drops bots into Google Meet for real-time trannoscripts.

Creator:   Vexa-ai
Stars ⭐️:  1,261
Forked by:  117

Github Repo:
https://github.com/Vexa-ai/vexa

#googlemeet  #meetingtrannoscription  #realtime
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

lerobot

This is an end-to-end library for robot learning. It handles the entire pipeline from loading and processing robotics datasets to training policies and deploying them in simulation or on real hardware.

Creator:   huggingface
Stars ⭐️:  19,000
Forked by: 3,000

Github Repo:
https://github.com/huggingface/lerobot

#robotics #AI
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

LightGBM

In simple terms, LightGBM is a gradient boosting framework that uses tree-based learning algorithms. It's designed to be faster, more efficient, and capable of handling large-scale data with lower memory usage than many other existing solutions.

Creator:   microsoft
Stars ⭐️:  55,000
Forked by:  18,000

Github Repo:
https://github.com/microsoft/LightGBM

#machinelearning  #gradientboosting
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

Wan2.2

Wan 2.2  is an open-source, large-scale video generative model. In simple terms, you give it a text prompt, and it generates a video that matches your denoscription. It's built on diffusion architecture, which has become the gold standard for high-quality generative models.

Creator:   Wan-Video
Stars ⭐️:  12,000
Forked by:  1,000

Github Repo:
https://github.com/Wan-Video/Wan2.2

#genai #videogeneration #opensource
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

LocalAI

The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more.
Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P and decentralized inference

Creator:   mudler
Stars ⭐️:  36,000
Forked by:  2,900

Github Repo:
https://github.com/mudler/LocalAI

#LLM #opensource
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

Scraperr

A self-hosted web-scraping tool you can deploy yourself, great for building personal datasets, scraping public info, or just learning scraping workflows end-to-end.

Creator:   jaypyles
Stars ⭐️:  4,600
Forked by:  234

Github Repo:
https://github.com/jaypyles/Scraperr

#web-scraping #opensource
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

no-as-a-service

Ever needed a polite (or hilarious) way to reject something without the awkwardness?
NaaS is a dead-simple API that returns a JSON response with a randomized rejection reason.

Creator:   hotheadhacker
Stars ⭐️:  3,000
Forked by:  212

Github Repo:
https://github.com/hotheadhacker/no-as-a-service

#Naas #reject #api
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

Final‑Year‑Project‑Ideas‑2025

A community-driven list of ~100 innovative and impactful project ideas for final-year students, covering AI, sustainability, education, health and more. It's perfect for inspiration or contributions.

Creator:   DharminJoshi
Stars ⭐️:  6
Forked by:  0

Github Repo:
https://github.com/DharminJoshi/Final-Year-Project-Ideas-2025

#projectideas #finalyearprojects
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group

iptv

This repository maintains an extensive collection of over 8,000 publicly accessible IPTV channels organized into neatly structured M3U playlists. These aren't pirated streams or sketchy links. They're legitimate public channels that broadcast freely online. The project categorizes everything by country, language, and content type, making it simple to find exactly what you're looking for.

Creator:   iptv
Stars ⭐️:  101,000
Forked by:  4,000

Github Repo:
https://github.com/iptv-org/iptv

#tvchannel #streaming #public
➖➖➖➖➖➖➖➖➖➖➖➖➖➖    
Join @github_repositories_bds for more cool repositories. This channel belongs to @bigdataspecialist group