Anmol BaranwalThe world is full of promising AI tools like Sora, ChatGPT, and more coming along the way.
I've gathered some mind-blowing AI tools that you must use.
The list includes an open source alternative of Devin AI, Notion, voice cloning in 5 seconds, email automation software, and tools you would never have heard of. Curiosity overload!
Don't forget to star them 🌟
Let's cover it all!
1. Taipy - Data and AI algorithms into production-ready web applications.
Taipy is an open source Python library for easy, end-to-end application development, featuring what-if analyses, smart pipeline execution, built-in scheduling, and deployment tools.
I'm sure most of you don't understand so Taipy is used for creating a GUI interface for Python-based applications and improving data flow management.
So, you can plot a graph of the data set and use a GUI-like slider to give the option to play with the data with other useful features.
While Streamlit is a popular tool, its performance can decline significantly when handling large datasets, making it impractical for production-level use.
Taipy, on the other hand, offers simplicity and ease of use without sacrificing performance. By trying Taipy, you'll experience firsthand its user-friendly interface and efficient handling of data.
Under the hood, Taipy utilizes various libraries to streamline development and enhance functionality.
Get started with the following command.
pip install taipy
Let's talk about the latest Taipy v3.1 release.
The latest release makes it possible to visualize any HTML or Python objects within Taipy's versatile part object.
This means libraries like Folium, Bokeh, Vega-Altair, and Matplotlib are now available for visualizations.
This also brings native support for Plotly python, making it easier to plot charts.
They have also improved performance using distributed computing but the best part is Taipy and all its dependencies are now fully compatible with Python 3.12 so you can work with the most up-to-date tools and libraries while using Taipy for your projects.
You can read the docs.
For instance, you can see the chat demo which uses OpenAI's GPT-4 API to generate responses to your messages. You can easily change the code to use any other API or model.
Another useful thing is that the Taipy team has provided a VSCode extension called Taipy Studio to accelerate the building of Taipy applications.
You can also deploy your applications with the Taipy cloud.
If you want to read a blog to see codebase structure, you can read Create a Web Interface for your LLM in Python using Taipy by HuggingFace.
It is generally tough to try out new technologies, but Taipy has provided 10+ demo tutorials with code & proper docs for you to follow along.
For instance, some live demo examples and project ideas:
Taipy has 7k+ Stars on GitHub and is on the v3 release so they are constantly improving.
2. PR Agent - Tool for Automated Pull Request Analysis, Feedback, Suggestions.
This is an open source tool to help efficiently review and handle pull requests. It has a bunch of unique options and offers extensive pull request functionalities across various git providers.
There are millions of open source projects with hundreds of Pull Requests every day so having a little friend that can help you is pretty neat.
I'm an open source maintainer so I know how tough it can get sometimes especially reviewing so many Pull Requests each day.
Anyway, this is how a PR Agent works under the hood.
You have to comment on the pull request with @CodiumAI-Agent /review, and the agent will respond with a review of the PR. There are a bunch of options available like describe & improve.
They also provide a list of PR-Agent tools, each with a dedicated page that explains how to use it.
You can read the docs and see example results.
The best part is that you can even run it as a GitHub Action. They also provide a pro version that has more options but the free tier is more than enough to get started.
If you are looking for good articles, I recommend Automating Pull Request Reviews With CodiumAI PR-Agent and 5 Reasons why CodiumAI PR-Agent is making developers’ lives easier. These give a lot of overview about PR Agent.
They have around 3.8k Stars on GitHub, used by over 300 developers, and are built using Python. While they may not be extremely popular, their use case is excellent.
3. Mintlify - Documentation that just appears as you build.
Mintlify is an AI-powered documentation writer and you can document code in just 1 second :D
I discovered Mintlify several months ago and I've been a fan of that ever since. I've seen a lot of companies use it, and even I generated complete docs using my business email which turns out to be very easy and decent. If you want detailed docs, Mintlify is the solution.
The other use case is generating docs based on the code which we are going to discuss here.
You can install the VSCode extension or install it on IntelliJ.
You just have to highlight the code or place the cursor on the line you want to document. Then click on the Write Docs button (or hit ⌘ + .)
You can read the docs and the security guidelines.
If you're more of a tutorial person then you can watch How Mintlify works. It supports more than 10 programming languages and supports a lot of docstring formats like JSDoc, reST, NumPy, and more.
By the way, their website link is writer.mintlify.com; the current one in the repo seems to be wrong.
It has around 2.4k stars on GitHub, is loved by many developers, and is built using TypeScript.
4. Screenshot to Code - Drop in a screenshot and convert it to clean code.
This is a very popular open source project but I can say for sure that a lot of developers still aren't aware of this. You can build a User Interfaces 10x faster using this.
It's a simple tool to convert screenshots, mockups, and Figma designs into clean, functional code using AI.
The app has a React/Vite frontend and a FastAPI backend. You will need an OpenAI API key with access to the GPT-4 Vision API or an Anthropic key if you want to use Claude Sonnet, or for experimental video support. You can read the guide to get started.
You can try it live on the hosted version and see the series of demo videos available on the wiki.
They have 47k+ Stars on GitHub and support a lot of tech stacks like React, and Vue with decent AI Models such as GPT-4 Vision, Claude 3 Sonnet, and DALL-E 3.
5. FaceSwap - Deepfakes Software For All.
I'm always fascinated by Deepfakes because that is how some AI works especially ones that use video.
Trust me! Many of us don't even use it to create videos, we just tinker with the code to see what it does and the unethical uses are not representative of why it was created, how we use it now, or what we see in its future.
You should watch this video to understand how a computer recognizes faces! Watch this video to understand the basic functioning of neural networks.
You can read INSTALL.md for the detailed installation guide. As per docs, you will need a modern GPU with CUDA support for best performance. Many AMD GPUs are supported through DirectML (Windows) and ROCm (Linux).
You can read the docs, see the demo video, and visit their blog to see video of conferences with other use cases.
The fact I loved the most is they have a very simple section on how anyone can contribute to the project including people interested in the generative models, developers, non-dev advanced users, end-users, and of course haters :)
They have 48k+ Stars on GitHub which makes them credible enough.
6. Amica - allows you to easily chat with 3D characters in your browser.
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
You can import VRM files, adjust the voice to fit the character, and generate response text that includes emotional expressions.
They use three.js, OpenAI, Whisper, Bakllava for vision, and many more. You can read on How Amica Works with the core concepts involved.
You can clone the repo and use this to get started.
npm i
npm run dev
You can read the docs and see the demo and it's pretty damn awesome :D
You can watch this short video on what it can do.
Amica uses Tauri to build the desktop application.
They have 400+ Stars on GitHub, and it seems very easy to use.
7. Bark - Text-Prompted Generative Audio Model.
Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise, and simple sound effects.
The model can also produce nonverbal communication like laughing, sighing, and crying. WOW!
It has an MIT License, meaning it's now available for commercial use.
Bark supports 100+ speaker presets across supported languages. You can see the library of supported voice presets here.
As per docs, Bark tries to match the tone, pitch, emotion, and prosody of a given preset but does not currently support custom voice cloning. The model also attempts to preserve music, ambient noise, etc. This is more than anyone needs.
This is how you can use this. Read this if you want to use it with the Transformers library.
from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav
from IPython.display import Audio
# download and load all models
preload_models()
# generate audio from text
text_prompt = """
Hello, my name is Suno. And, uh — and I like pizza. [laughs]
But I also have other interests such as playing tic tac toe.
"""
audio_array = generate_audio(text_prompt)
# save audio to disk
write_wav("bark_generation.wav", SAMPLE_RATE, audio_array)
# play text in notebook
Audio(audio_array, rate=SAMPLE_RATE)
Bark supports various languages out of the box and automatically determines language from input text. When prompted with code-switched text, Bark will attempt to employ the native accent for the respective languages.
You can read the docs and see the demo at Google Colab & Replicate.
You can also read about voice consistency enhancements, and other forms of examples in the notebook section.
They support a lot of languages like English, Hindi, German, French, and more.
They have 30k+ Stars on GitHub and running a community of 300000+ makes them a worthy choice.
8. GPTDiscord - all-in-one GPT interface for Discord.
I'm part of several communities on Discord and bots with excellent use cases can improve the overall end user experience.
This bot is on feature parity with ChatGPT web and even does some things slightly better!
They support everything from multi-modality image understanding, code interpretation, advanced data analysis, Q&A on your documents, internet-connected chat with Wolfram Alpha and Google access, AI moderation, image generation with DALL-E, and much more!
You can read about all the efficient features of GPTDiscord.
You can read the installation guide.
You can see the screenshots and see the list of detailed guides for different purposes.
They have around 1.8k+ Stars on GitHub and are definitely improving.
9. Upscayl - open source AI image upscaler.
Free and Open Source AI Image Upscaler for Linux, MacOS, and Windows built with Linux-First philosophy.
It might not be related to full-stack, but it can be useful for upscaling your images.
With state-of-the-art AI, Upscayl helps you turn low-resolution images into high resolution. Crisp and sharp!
You can read the installation guide, and check out the Upscayl before/after comparisons.
It has 23k+ Stars on GitHub and is built upon TypeScript.
10. AppFlowy - open source alternative to Notion.
AppFlowy is an AI-powered secure workspace similar to the notion where you achieve more without losing control of your data.
They also provide mobile apps so that's a plus.
You can read the docs and read about installation methods.
They also support self-hosting AppFlowy using Supabase. This is ideal for users who prefer Supabase's features or use Supabase for their infrastructure.
You should also check this to learn more about data storage, markdown, shortcuts, themes, AI involved, and plugins.
AppFlowy has 47k+ Stars on GitHub with 64+ releases.
11. Leon - your open source personal assistant.
Leon is an open source personal assistant who can live on your server.
He does stuff when you ask him to.
You can talk to him and he can talk to you. You can also text him and he can also text you. If you want to, Leon can communicate with you by being offline to protect your privacy. This is a list of skills that Leon can do for now.
You should read the story behind Leon. You can also watch this demo to learn more about Leon.
This is the High-level architecture schema of Leon.
This is how you can get started using the npm command.
# install leon global cli
npm install --global @leon-ai/cli
# install leon
leon create birth
You can read the docs.
It has 14k+ Stars on GitHub and still growing.
12. n8n - workflow automation tool.
n8n is an extendable workflow automation tool. With a fair-code distribution model, n8n will always have visible source code, be available to self-host, and allow you to add your custom functions, logic, and apps.
n8n's node-based approach makes it highly versatile, enabling you to connect anything to everything.
There are 400+ integration options which is almost insane!
You can see all the options for installation including Docker, npm & self-host.
Get started with the following command.
npx n8n
This command will download everything that's needed to start n8n. You can then access n8n and start building workflows by opening http://localhost:5678.
Watch this quickstart video on YouTube!
You can read the docs and read this guide to quickly start based on your needs.
They also provide beginner and intermediate courses to follow along easily.
They have 39k+ Stars on GitHub and provide two packages for the overall usage.
13. Quivr - your GenAI Second Brain.
Quivr, your second brain, utilizes the power of GenerativeAI to be your personal assistant! Think of it as Obsidian, but turbocharged with AI capabilities.
You can read the installation guide.
You can read the docs and see the demo video.
They could provide a better free tier plan but it's more than enough to test things on your end.
It has 30k+ Stars on GitHub with 220+ releases which means they're constantly improving.
14. meilisearch - search API that fits in your apps, websites, and workflow.
Meilisearch helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
You must have seen software websites where you can search the docs by using Ctrl + k like GitHub or Appwrite. Well, meilisearch can help you implement the same.
Compared to Algolia, Typesense, and Elasticsearch this is the only one that is built on Rust. You can read about comparison to alternative options available :)
Meilisearch should not be your main data store. It is a search engine, not a database. Meilisearch should contain only the data you want your users to search through. If you must add data that is irrelevant to the search, be sure to make those fields non-searchable to improve relevancy and response time.
Meilisearch provides an intuitive search-as-you-type experience with response times under 50 milliseconds, no matter whether you are developing a site or an app.
They provide SDKs and libaries for seamless integration between Meilisearch and your favorite language or framework. Trust me, the number of options is insane.
They also provide a scraper tool to automatically read the content of your documentation and store it into Meilisearch.
They have showcased a lot of useful features such as you can get relevant matches even when queries contain typos and misspellings which they name typo tolerance.
There are a lot of options available, but let's look at how we can do it using React.
Get started with the following command.
yarn add react-instantsearch @meilisearch/instant-meilisearch
# or
npm install react-instantsearch @meilisearch/instant-meilisearch
# or
pnpm add react-instantsearch @meilisearch/instant-meilisearch
This is how you can use this.
import React from 'react';
import { InstantSearch, SearchBox, Hits, Highlight } from 'react-instantsearch';
import { instantMeiliSearch } from '@meilisearch/instant-meilisearch';
const { searchClient } = instantMeiliSearch(
'https://ms-adf78ae33284-106.lon.meilisearch.io',
'a63da4928426f12639e19d62886f621130f3fa9ff3c7534c5d179f0f51c4f303'
);
const App = () => (
<InstantSearch
indexName="steam-video-games"
searchClient={searchClient}
>
<SearchBox />
<Hits hitComponent={Hit} />
</InstantSearch>
);
const Hit = ({ hit }) => <Highlight attribute="name" hit={hit} />;
export default App
You can see this codesandbox for a detailed example to get started.
As I said, they provide a lot of things under the hood. For instance, you can use these.
npm install @meilisearch/autocomplete-client
npm install @meilisearch/instant-meilisearch
npm install meilisearch-docsearch
meilisearch docsearch is inspired by the Algolia search documentation component. Plus, very detailed docs with examples & options for each of sdk just make them a complete favorite.
You can read the docs and see the live demo.
They have 42k+ Stars on GitHub and are on the v1.7 with 180+ releases.
15. Inbox Zero - Clean Up Your Inbox In Minutes.
Inbox Zero is an open source email app whose goal is to help you reach inbox zero fast with AI assistance.
They are approved by Google so that's a good part of focusing on privacy.
They use Postgres for the database and are built on TypeScript.
They have some insane features such as:
Your AI assistant for email
The AI agent will let you automate replies, and forward, or archive emails based on the rules you provide.
Their AI plan can help you Accept or reject in a click. Turn on full automation once you're confident the AI can work on its own.
You can instruct in plain English. It's as easy as talking to an assistant or sending a prompt to ChatGPT.
You can automatically block cold emails
You can tell Inbox Zero what constitutes a cold email for you. It will block them based on your instructions.
Analytics
Understanding your inbox is the first step to dealing with it. Understand what is filling up your inbox. They also give a way for you to take instant action.
You can read about the core features and watch the demo video. You can also see their kanban to see what is planned.
They have 1.5k+ Stars on GitHub and definitely deserve a whole lot more.
16. Lively - allows users to set animated desktop wallpapers and screensavers.
This is just for fun and we can learn a lot using the code on how it's done.
You can see this video on how insane it looks.
They provide three types of wallpapers including video/GIF, Webpage, and Application/Games.
It is built on C# and some of the cool features that lively supports:
Lively can be controlled with command line arguments from the terminal. You can integrate this with other languages like Python or scripting software AutoHotKey.
Powerful set of API for developers to create interactive wallpapers. Get hardware readings, audio graphs, music information, and more.
Wallpaper playback pauses when fullscreen applications/games run on the machine (~0% CPU, GPU usage).
You can also leverage Machine Learning inference to create dynamic wallpapers. You can predict the distance from the camera of any 2D image and generate a 3D-like parallax effect. Cool :D
I've seen a lot of people using it and many of them aren't even aware that it's open source.
You can download it using installer or through microsoft store.
It was the winner of 2023 on the Microsoft Store.
It has 13k+ Stars on GitHub with 60 releases.
17. Netron - Visualizer for neural network, deep learning, and machine learning models.
Netron is a viewer for neural networks, deep learning, and machine learning models.
Netron supports ONNX, TensorFlow Lite, Core ML, Keras, Caffe, Darknet, MXNet, PaddlePaddle, ncnn, MNN, and TensorFlow.js.
Netron has experimental support for PyTorch, TorchScript, TensorFlow, OpenVINO, RKNN, MediaPipe, ML.NET, and scikit-learn.
You can read about installation instructions.
You can visit the website and open these sample model files to open using that. For instance, you can see this demo.
They have 25k+ Stars on GitHub and are built on JavaScript. They are on the v7.5 with just three releases which seems confusing to me considering I've only used the semantic version. We all can agree that the use case is very excellent.
18. Cursor - AI-powered code editor based on VSCode.
Cursor is a code editor designed for pair programming with AI. Cursor is available for Windows, Mac & Linux.
Cursor is not just a Visual Studio Code (VSC) extension. It’s its own application. But don’t worry! It’s a VSC fork. This means it has everything VSC has but with a lot more AI features built on top of it.
https://github.com/anysphere/priompt
They previously open sourced their Codemirror-based editor.
The VSCodium-based version of Cursor is not open source and only their prompting library is open source.
The amount of options is huge, and you can check the list of features such as choosing your AI model for chat, codebase indexing, and Auto Terminal Debug. Sounds cool, right :D
Some of the features you should check out are:
- Allow you to code by editing a "pseudocode" version of your codebase.
- Auto-fix errors as soon as they show up in your terminal.
- Ask the AI to change a block of code, see an inline diff of the edits.
You can also read about the changelog of their official website.
You can read about how to migrate from VSCode to Cursor.
They also have a pricing model but the free tier is enough for you to test it through!
They have 19k+ Stars on GitHub and will continue to grow. As I said, that's not open source but could change in the future.
19. VSCode Debug Visualizer - extension for VS Code that visualizes data during debugging.
This project is quite impressive. Not only does it help with efficient debugging, but it also helps in learning fundamental concepts through visualization, which is invaluable in the long run.
This is a VS Code extension for visualizing data structures while debugging. Like the VS Code's watch view, but with rich visualizations of the watched value.
They support a lot of languages such as Dart/Flutter, JS/TS, Go, Python, C#, Java, C++, Ruby, Rust, and Swift even though it's basic so that's a plus point.
Other languages and debuggers might also work. For languages with basic support, only JSON strings can be visualized. You'll need to implement logic to build this JSON for your data structure. Fully supported languages offer data extractors that convert some well-known data structures to JSON.
You can use the command Debug Visualizer: New View to open a new visualizer view after installing the extension.
You can see all the demos that are available and see the extension at marketplace.
You can also check out their visualization playground with numerous options.
They have 7.8k+ Stars on GitHub and it's growing.
Star VSCode Debug Visualizer ⭐️
20. OpenDevin - Code Less, Make More.
This an open source project aiming to replicate Devin, an autonomous AI software engineer who is capable of executing complex engineering tasks and collaborating actively with users on software development projects. This project aspires to replicate, enhance, and innovate upon Devin through the power of the open source community.
Just to let you know, this was way before Devin was introduced.
You can read the installation instructions with requirements.
They use LiteLLM, so you can run OpenDevin with any foundation model, including OpenAI, Claude, and Gemini under the hood.
You can see the demo and contributing guidelines if you're looking to contribute to OpenDevin.
It has 10.7k+ Stars on GitHub and is growing at a rapid pace.
21. Real Time Voice Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time.
This project is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real time.
SV2TTS is a deep learning framework in three stages.
In the first stage, one creates a digital representation of a voice from a few seconds of audio.
In the second and third stages, this representation is used as a reference to generate speech given arbitrary text.
You can read on how to setup the project which includes install requirements, downloading Pretrained Models, Test Configuration, downloading datasets, and launching the Toolbox.
Watch the video demonstration shown below!
The best part I always like about open source projects is that they even mention the alternatives very clearly and as usual they have recommended some projects that will give better fidelity of the voice you're cloning and its expressivity.
They have 50k+ Stars on GitHub and are only built on Python. It is very credible to use to date.
Star Real Time Voice Cloning ⭐️
Let me know in the comments on what useful AI tools you found in this list :D
AI is changing the world and it's better to keep AI as your friend rather than simply ignore it.
Use these tools to be productive and take the chance to create something extraordinary.
Have a great day! Till next time.
Follow me on GitHub, and Twitter.
Anmol-Baranwal (Anmol Baranwal) · GitHub
Top 5% GitHub 💜 Open Source Advocate & Maintainer 😄 Full-Stack Developer 🔖 Technical Writer (400k+ Reads) 🔥 Managing 5+ Communities 🚀 Open for Collab - Anmol-Baranwal
github.com
Follow Taipy for more content like this.
