Welcome to our weekly roundup of the Top 10 Trending GitHub Repositories for the week of October 28, 2024. Whether youβre a developer, data scientist, or tech enthusiast, these repositories have garnered significant attention on GitHub this week. Letβs dive into what makes these projects stand out!
1. Phidatahq / Phidata
Description: Build AI Agents with memory, knowledge, tools, and reasoning. Chat with them using a beautiful Agent UI.
Link to Repository: Visit Repository
phidatahq / phidata
Build multi-modal Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.
phidata
Build multi-modal Agents with memory, knowledge, tools and reasoning
What is phidata?
Phidata is a framework for building multi-modal agents, use phidata to:
- Build multi-modal agents with memory, knowledge, tools and reasoning.
- Build teams of agents that can work together to solve problems.
- Chat with your agents using a beautiful Agent UI.
Install
pip install -U phidata
Key Features
- Simple & Elegant
- Powerful & Flexible
- Multi-Modal by default
- Multi-Agent orchestration
- A beautiful Agent UI to chat with your agents
- Agentic RAG built-in
- Structured Outputs
- Reasoning Agents
- Monitoring & Debugging built-in
- Demo Agents
Simple & Elegant
Phidata Agents are simple and elegant, resulting in minimal, beautiful code.
For example, you can create a web search agent in 10 lines of code, create a file web_search.py
from phi.agent import Agent
from phi.model.openai import OpenAIChat
from phi.tools.duckduckgo import DuckDuckGo
web_agent =
β¦2. Hiteshchoudhary / Apihub
Description: Your own API Hub to learn and master API interaction. Ideal for frontend, mobile dev, and backend developers.
Link to Repository: Visit Repository
hiteshchoudhary / apihub
Your own API Hub to learn and master API interaction. Ideal for frontend, mobile dev and backend developers.
FreeAPI.app
Problem
We are trying to build a single source API hub that can be used to learn api handling in any programming language. Users can build their front end portfolio in web and mobile apps using this api hub.
What is FreeAPI.app
The FreeAPI project is an innovative and community-driven initiative aimed at providing developers with free and accessible APIs for their projects.
The project focuses on delivering a wide range of APIs that cater to various domains and functionalities, enabling developers to seamlessly integrate these APIs into their applications.
Key highlights of the FreeAPI project include:
-
Accessibility: The FreeAPI project is committed to eliminating barriers by providing free access to its collection of APIs Developers can leverage these APIs without any cost limitations, allowing them to experiment, learn, and build innovative applications.
-
Diverse API Collection: The project offers a diverse and comprehensive collection of APIs that span acrossβ¦
3. OpenInterpreter / Open-interpreter
Description: A natural language interface for computers
Link to Repository: Visit Repository
OpenInterpreter / open-interpreter
A natural language interface for computers
β Open Interpreter
Get early access to the desktop appβ β |β β Documentation
Note
Open Interpreter 1.0 is almost here.
Please help test the development branch and share your experience in the Discord:
pip install git+https://github.com/OpenInterpreter/open-interpreter.git@development
interpreter --help
pip install open-interpreter
Not working? Read our setup guide.
interpreter
Open Interpreter lets LLMs run code (Python, Javascript, Shell, and more) locally. You can chat with Open Interpreter through a ChatGPT-like interface in your terminal by running $ interpreter
after installing.
This provides a natural-language interface to your computer's general-purpose capabilities:
- Create and edit photos, videos, PDFs, etc.
- Control a Chrome browser to perform research
- Plot, clean, and analyze large datasets
- ...etc.
Demo
Open.Interpreter.Demo.mp4
An interactive demo is also available on Google Colab:
Along with an example voice interface, inspired by Her:
Quick Start
pip install
β¦4. Kolbytn / Mindcraft
Description: Crafting minds for Minecraft with Language Models and Mineflayer!
Link to Repository: Visit Repository
Mindcraft π§ βοΈ
Crafting minds for Minecraft with LLMs and Mineflayer!
FAQ | Discord Support | Blog Post | Contributor TODO
βΌοΈ WarningβΌοΈ
Do not connect this bot to public servers with coding enabled. This project allows an LLM to write/execute code on your computer. While the code is sandboxed, it is still vulnerable to injection attacks on public servers. Code writing is disabled by default, you can enable it by setting allow_insecure_coding
to true
in settings.js
. We strongly recommend running with additional layers of security such as docker containers. Ye be warned.
Requirements
- Minecraft Java Edition (up to v1.21.1, recommend v1.20.4)
- Node.js Installed (at least v14)
- One of these: OpenAI API Key | Gemini API Key | Anthropic API Key | Replicate API Key | Hugging Face API Key | Groq API Key | Ollama Installed. | Mistral API Key | Qwen API Key [Intl.]/[cn]β¦
5. Drawdb-io / Drawdb
Description: Free, simple, and intuitive online database diagram editor and SQL generator.
Link to Repository: Visit Repository
Free, simple, and intuitive database schema editor and SQL generator.
DrawDB is a robust and user-friendly database entity relationship (DBER) editor right in your browser. Build diagrams with a few clicks, export sql scripts, customize your editor, and more without creating an account. See the full set of features here.
Getting Started
Local Development
git clone https://github.com/drawdb-io/drawdb
cd drawdb
npm install
npm run dev
Build
git clone https://github.com/drawdb-io/drawdb
cd drawdb
npm install
npm run build
Docker Build
docker build -t drawdb .
docker run -p 3000:80 drawdb
Set up the server and environment variables according to .env.sample
for the survey and bug report forms.
6. Getomni-ai / Zerox
Description: Zero-shot PDF OCR with GPT-4o-mini
Link to Repository: Visit Repository
getomni-ai / zerox
PDF to Markdown with vision models
Zerox OCR
A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense!
The general logic:
- Pass in a file (pdf, docx, image, etc.)
- Convert that file into a series of images
- Pass each image to GPT and ask nicely for Markdown
- Aggregate the responses and return Markdown
Try out the hosted version here: https://getomni.ai/ocr-demo
Getting Started
Zerox is available as both a Node and Python package.
Node Zerox
npm install zerox
Zerox uses graphicsmagick
and ghostscript
for the pdf => image processing step. These should be pulled automatically, but you may need to manually install.
On linux use:
sudo apt-get update
sudo apt-get install -y graphicsmagick
Usage
With file URL
import { zerox } from "zerox";
β¦7. Ranaroussi / Yfinance
Description: Download market data from Yahoo! Finance's API
Link to Repository: Visit Repository
ranaroussi / yfinance
Download market data from Yahoo! Finance's API
Download market data from Yahoo! Finance's API
*** IMPORTANT LEGAL DISCLAIMER ***Yahoo!, Y!Finance, and Yahoo! finance are registered trademarks of Yahoo, Inc. yfinance is not affiliated, endorsed, or vetted by Yahoo, Inc. It's an open-source tool that uses Yahoo's publicly available APIs, and is intended for research and educational purposes. You should refer to Yahoo!'s terms of use (here here, and here) for details on your rights to use the actual data downloaded. Remember - the Yahoo! finance API is intended for personal use only. |
yfinance offers a Pythonic way to fetch financial & market data from Yahoo!β finance.
Main components
-
Ticker
: single ticker data -
Tickers
: multiple tickers' data -
download
: download market data for multiple tickers -
Search
: quotes and news from search -
Sector
andIndustry
: sector and industry information -
EquityQuery
andScreener
: build query to screen market
NEW
β¦8. Facebookresearch / Co-tracker
Description: CoTracker is a model for tracking any point (pixel) on a video.
Link to Repository: Visit Repository
facebookresearch / co-tracker
CoTracker is a model for tracking any point (pixel) on a video.
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
Meta AI Research, GenAI; University of Oxford, VGG
Nikita Karaev, Iurii Makarov, Jianyuan Wang, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht
Project Page | Paper #1 | Paper #2 | X Thread | BibTeX
CoTracker is a fast transformer-based model that can track any point in a video. It brings to tracking some of the benefits of Optical Flow.
CoTracker can track:
- Any pixel in a video
- A quasi-dense set of pixels together
- Points can be manually selected or sampled on a grid in any video frame
Try these tracking modes for yourself with our Colab demo or in the Hugging Face Space π€.
Updates:
-
[October 15, 2024] π£ We're releasing CoTracker3! State-of-the-art point tracking with a lightweight architecture trained with 1000x less data than previous top-performing modelsβ¦
9. Bluesky-social / Social-app
Description: The Bluesky Social application for Web, iOS, and Android
Link to Repository: Visit Repository
bluesky-social / social-app
The Bluesky Social application for Web, iOS, and Android
Bluesky Social App
Welcome friends! This is the codebase for the Bluesky Social app.
Get the app itself:
- Web: bsky.app
- iOS: App Store
- Android: Play Store
Development Resources
This is a React Native application, written in the TypeScript programming language. It builds on the atproto
TypeScript packages (like @atproto/api
), code for which is also open source, but in a different git repository.
There is a small amount of Go language source code (in ./bskyweb/
), for a web service that returns the React Native Web application.
The Build Instructions are a good place to get started with the app itself.
The Authenticated Transfer Protocol ("AT Protocol" or "atproto") is a decentralized social media protocol. You don't need to understand AT Protocol to work with this application, but it can help. Learn more at:
- Overview and Guides
- Github Discussions π Great place to ask questions
- Protocol Specifications
- Blogpost onβ¦
10. Cocos / Cocos-engine
Description: Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine for 2D/3D games and instant web entertainment.
Link to Repository: Visit Repository
cocos / cocos-engine
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D games and instant web entertainment.
Engine for Cocos Creator
Cocos Creator is the new generation of game development tool in Cocos family, it brings a complete set of 3D and 2D features while providing an intuitive, low cost and collaboration friendly workflow to game developers. Cocos Engine is the runtime framework for Cocos Creator editor.
Cocos Creator inherited many good qualities and cool features from its previous versions, such as high performance low level C++ implementation, intuitive editor, cross-platform support. It supports native platforms, web platforms and rapidly expanding instant gaming platforms, including Windows, Mac, iOS, Android, HarmonyOS, Web, Facebook Instant Games, WeChat Mini Game and TikTok Mini Games.
Furthermore, Cocos Creator has pushed the engine technology to a whole new level for high performance with scalability on various platforms, full extensibility and easy development.
- Modern Graphics: The GFX implementation is designed to adapt to the modern graphics APIs, it uses Vulkan on Windowsβ¦
Honorable Mentions
Here are a few repositories that didnβt make the top 10 but deserve a mention this week:
PowerShell / PowerShell
PowerShell is a cross-platform (Windows, Linux, and macOS) automation and configuration tool/framework that works well with your existing tools and is optimized for dealing with structured data (e.g. JSON, CSV, XML, etc.)Sveltejs / Svelte β Web development for the rest of us.
Anthropics / Courses β Anthropic's educational courses.
Infiniflow / Ragflow β RAGFlow is an open-source RAG engine based on deep document understanding.
Serengil / Deepface
β A lightweight face recognition and facial attribute analysis library for Python.
Conclusion
That concludes our Top 10 Trending GitHub Repositories for the week of October 28, 2024! Be sure to explore these projects, contribute if possible, and stay tuned for next weekβs roundup of trending repositories.
Join the Daily dev Nuxt & vue Squad
Nuxt Modules start of the week
Formkit
Description: # FormKit equips developers to build their forms 10x faster by simplifying form structure, generation, validation, theming, submission, error handling, and more.
Here is a example of How to use FormKit,Nuxt,Better Auth & Drizzle:
leamsigc / nuxt-better-auth-drizzle
Nuxt 4 Integration with Better auth and Drizzle ORM
Nuxt and Better Auth integration example | Step by step tutorial | Basic Setup
- User registration | email and password
- User login | email and password
- User logout
Protected routes
/app/
Unprotected routes
/login
/register
/
- Create new Nuxt 4 project
-
Install Basic modules for the project
- Tailwind css
- SEO Module
- Vue Use
- Drizzle ORM
- Install Drizzle ORM
pnpm add drizzle-orm @libsql/client dotenv
pnpm add -D drizzle-kit tsx
-
Create
.env
-
Create config Drizzle
-
Create schema
- Nuxt Image
- Nuxt font
- Nuxt scripts
- Nuxt content
- Formkit
-
Create the config file for the FormKit
-
Update the nuxt.config file
-
Install the theme for the FormKit styles
npx formkit theme --theme=regenesis
-
Include the FormKit theme config to the tailwindcss configuration
-
There is a issue with Formkit and Nuxt when setting the
autimport:true
in the Formkit config to FormKitSchema have an issue with the data banding.
Optional Modules:
- tailwind-variants
- typographty β Tailwind css
- @unlighthouse/nuxt
npx nuxi@latest
β¦
Happy hacking!
Working on the audio version
Top comments (2)
In the "Honorable Mentions" titles mismatch the descriptions (descriptions seem to be upshifted)
Thank you very much for the feedback :D