Anmol BaranwalGoogle is getting older and developers are now using modern AI Chat tools to complete all the programming tasks.
This is the list of 11 open source projects with the best AI chat interface to help you maximize your productivity.
I have referenced tutorials and awesome features to make it easier for you to decide which one is best for you.
Let's do it.
1. LLMChat - Most intuitive All-in-one AI chat interface.
I've tested all the tools and I believe LLMChat is one of the best ones out there.
I love this especially because of how clean the user interface looks. I don't even need a tutorial to understand most of the stuff.
This is what the dashboard looks like.
Let's see some of the features that make it 10x powerful.
✅ Supports various language models, including GPT 4o Mini, Ollama, Claude, Groq and lm studio (coming soon). You can also use local models if you want. They offer their own free model if you're just getting started.
✅ The feature I loved the most is they offer a plugin system, including function calling capabilities which makes it next level.
For instance, let's see a couple of plugins in action.
-→ Web Search: Allows AI to fetch and utilize real-time web data.
As you can see, it gives a response based on the recent web search results. One of my articles is referenced as well.
-→ Memory: This helps in personalizing future interactions.
✅ You can even attach an image for the context.
✅ It will give you related search results suggestions as well. For instance, I searched about how to contribute to open source projects and this is the result.
✅ You also get a prompt library where you can find pre-defined prompts or create your own.
✅ Their settings also have a bunch of options like you can import/export data, enable Whisper Speech-to-Text and more.
✅ You can also search the conversations so it's the manual lookout. It will be much faster especially if you create your own titles for the conversations.
✅ It securely stores data locally using in-browser IndexedDB for faster access and privacy. Read the privacy policy.
✅ They are planning to launch a feature called Knowledge Spaces which will be custom knowledge bases for specialized topics. I would love to see it in action!
What more do you need?
It is built on my favorite tech stack using Next.js, TypeScript, Pglite, LangChain, Zustand, React Query, Supabase, Tailwind CSS, Framer Motion, Shadcn and Tiptap.
You can check the demo at llmchat.co/chat and share your feedback.
I don't think I need anything else since prompts and plugins are more than enough for me as a developer. Also, if you are a fan of app-like experience, they support PWA as well.
LLMChat is open source with 133 stars on GitHub. It's in the early stage but it will grow very fast.
2. Open WebUI - most loved AI Interface (Supports Ollama, OpenAI API...), runs offline.
Open WebUI is an awesome user-friendly self-hosted chat user interface designed to operate entirely offline.
You will have to install it to properly use it offline.
You can use pip to quickly install it. Check the complete installation guide.
# install Open WebUI
pip install open-webui
# run Open WebUI
open-webui serve
Let's see some of the awesome features.
✅ You can customize the OpenAI API URL to link with LMStudio, GroqCloud, Mistral, OpenRouter and more.
✅ You can use it in your preferred language with our internationalization (i18n) support.
✅ There is an option of hands-free voice and video call features which gives a little more flexibility.
✅ Their official website has clear info on a bunch of models, prompts, tools and functions by the community.
✅ You can load documents directly into the chat or add files to your document library and access them using the # command before a query.
✅ You can perform web searches using providers like SearXNG, Google PSE, Brave Search, serpstack, serper, Serply, DuckDuckGo, TavilySearch and SearchApi to inject the results directly into your chat experience.
Also recommend watching this walkthrough to learn more.
You can read the docs which includes a getting started guide, FAQs (recommend reading) and tutorials.
It is built using Svelte, Python and TypeScript.
They have 41.6k stars on GitHub which says a lot about the popularity.
3. LibreChat - ChatGPT clone but 100x better.
LibreChat brings together the future of assistant AIs using OpenAI's ChatGPT. It can also integrate and improve original client features such as conversation and message search, prompt templates and plugins.
With LibreChat, you no longer need to opt for ChatGPT Plus and can instead use free or pay-per-call APIs.
You can check the live demo at librechat-librechat.hf.space.
You can watch this demo to learn more.
Let's see some of the awesome features:
✅ You can add multi-conversation. And use Speech to Text (STT) and Text to Speech (TTS).
✅ The collection of models is insane such as Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, BingAI, ChatGPT, Google Vertex AI, Plugins, Assistants API (including Azure Assistants). This gives you complete power and lots of choices.
✅ You can attach files and chat using Custom Endpoints, OpenAI, Azure, Anthropic & Google.
✅ You can edit, Resubmit, and Continue Messages with Conversation Branching. It's available in 20+ languages.
✅ You can create, Save, & Share Custom Presets. Plus, you can even export chats as Screenshots, Markdown, Text and JSON.
It's not possible to break down all the extensions and plugins so please explore yourself.
You can check all these features in detail on the docs.
You can read the docs which includes user guides, plugins, detailed installation guides and more.
LibreChat is very famous in the community and you can understand why after reading this.
They have 18k stars on GitHub and are built using TypeScript.
4. Chatbot UI - most loved chatbot template out there.
This is a much more popular chatbot compared to the Vercel chatbot and this one has syntax highlighting which was referenced in Vercel.
I was working on a project a long time ago and it's mentioned in the component as far as I believe.
Anyway, here is a complete demo.
They don't have a lot of fancy features but support most of the stuff any person would ever need.
You can get your own Chatbot UI instance running in the cloud or you can even run locally.
You can check the live demo at chatbotui.com.
One thing to note is you will have to use your own OpenAI API key even by default.
They have 28.5k stars on GitHub and are built using TypeScript.
5. Vercel Chatbot - chatbot template by Vercel.
This one is created by Vercel and it uses Vercel AI SDK which is based on Nextjs.
This is how the dashboard looks.
This is more like a template as a chatbot rather than a complete interface to use the latest models.
This template ships with OpenAI gpt-3.5-turbo as the default. But thanks to the Vercel AI SDK, you can switch LLM providers to Anthropic, Cohere, Hugging Face or use LangChain with just a few lines of code.
You can install and use it locally as well if you wish.
They have 6.3k stars on GitHub and aren't very great in terms of features.
6. Deep Chat - AI chat component to inject into your website.
Deep Chat is a fully customizable AI chat component that can be used for your website with absolutely no effort.
You can check the live demo at deepchat.dev/playground.
✅ It can also be used to create new files inside the component! Click the camera button to capture photos or use the microphone button to record audio.
✅ You can also use speech-to-text.
This is how you can get started in case you're using React.
npm install deep-chat-react
// add this to the markup
<deep-chat></deep-chat>
After that, you can simply connect based on your requirements.
The exact syntax might differ based on your framework. They have clearly documented it in their examples.
You can read the docs which includes the installation guide.
They have 1.4k stars on GitHub and are built using TypeScript.
7. Huggingface Chat - HuggingChat app using open source models like Llama.
A chat interface using open source models, eg OpenAssistant or Llama. This is a SvelteKit app and it powers the HuggingChat app.
This is one of the most loved AI Chat interfaces out there and for obvious reasons.
If you prefer watching tutorials, then I recommend watching this one.
Let's see some of the awesome features.
✅ They provide 182 useful community tools that you can filter based on trending and popular.
✅ They provide a lot of assistants which you can choose based on the models. Recommend reading the official discussion on this.
✅ You can choose good models and describe a system prompt which is another way to customize your experience.
You can read the docs where you can find more info about architecture and the quickstart guide.
They have 7.3k stars on GitHub and are built on TypeScript.
8. SpeechGPT - Chat using GPT with a focus on speech.
SpeechGPT is a web application that enables you to converse with ChatGPT.
You can utilize this app to improve your language-speaking skills or simply have fun chatting with ChatGPT.
Most of you would say what's unique about this but it actually is.
Let's break some awesome features:
✅ All the data is stored locally which leads to stronger privacy.
✅ As per docs, it supports over 100 languages but I can only see support for three languages on the live demo.
✅ Includes both built-in speech recognition and integration with Azure Speech Services.
✅ Includes built-in speech synthesis, as well as integration with Amazon Polly and Azure Speech Services.
Follow this tutorial in docs to understand how to use this.
You can see the live demo at speechgpt.app. This is a perfect example of how a couple of extra features can take your app to the next level!
SpeechGPT has 2.7k stars on GitHub and is on the v0.5.1 release.
9. NextChat - A cross-platform ChatGPT and Gemini UI.
All you need is a One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support (Web / PWA / Linux / Win / MacOS).
Some of the awesome features are:
✅ Privacy First, all data is stored locally in the browser.
✅ Automatically compresses chat history to support long conversations while also saving your tokens.
✅ Compact client (~5MB) on Linux/Windows/MacOS.
✅ You can deploy for free with one click on Vercel in under 1 minute.
✅ Fully compatible with self-deployed LLMs.
✅ Markdown support: LaTex, mermaid, code highlight, etc.
You can check the live demo of NextChat and the docs including the list of all env variables mainly API keys.
It's not hard to work on it locally and they have also provided a GitHub actions workflow that will automatically update it every hour.
NextChat has 75.5k+ stars on GitHub and are on the v2.2 release.
10. GPT4All - Run Local LLMs on Any Device.
GPT4All runs large language models (LLMs) privately. You don't need any API calls or GPUs.
Just download the app from the official website and get started. It's available for Windows, MacOS and Ubuntu.
If you're looking for a tutorial, I recommend watching this.
Let's quickly take a look at some awesome stats.
✅ You can use GPT4All LLMs with your sensitive local data without it ever leaving your device.
✅ GPT4All allows you to run LLMs on CPUs and GPUs. It fully supports Mac M Series chips, AMD, and NVIDIA GPUs.
✅ You can chat with your local files.
✅ As per the official website, there are over 1000 open source language models that are available. It is kind of an insane number.
✅ You can customize your chatbot experience with your own system prompts, temperature, context length, batch size, and more
This is how the dashboard of the desktop client looks.
You can explore models and it will show if that is compatible with your nice system. You can insert the API key there itself and filter these.
You can read the docs including the quick start guide and info about all the models. They also provide a Python SDK if you want to incorporate it into your codebase.
I would also recommend reading official blog on the release of GPT4All 3.0 Desktop App.
They have 69.8k stars on GitHub and are built using C++.
11. Jan - open source alternative to ChatGPT that runs 100% offline with multiple engine support (llama.cpp, TensorRT-LLM).
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
You will have to download it based on your Operating System. The best part is that there is no paid version for Jan.
Here is a quick demo of Jan.
There are a lot of features like personalized AI assistants and extensions that you can explore yourself.
You can read the docs which includes a quickstart guide and info on the models used. You can connect with your files but it's still an experimental feature.
You can even integrate Jan with the Continue code editor which makes things very interesting. Read the guidelines in the docs.
If you're looking for a tutorial, watch this demo.
They have a total downloads of 1.7M+ so that makes them very credible since they have a large community.
Jan has 22.6k stars on GitHub and was built using TypeScript.
Developers are now switching from conventional tools like GPT and google to these advanced options.
LLMChat and OpenWeb UI are my favorites because I prefer clean user experience.
Have a great day! Till next time.
| If you loved this, please follow me for more :) |
  
|
|---|
