OmniBot: Your Native AI Assistant

This is a private AI that uses WebGPU to run LLMs natively & privately in your browser, bringing you in-browser AI experience.

Nextjs Starter Kit Dashboard Preview

OmniBot: Native Artificial Intelligence

Bringing you in-browser and offline AI experience with selected LLMs

Offline chat
Once the initial download of a model is processed, you will be able to use omnibot without an internet connection.
In-browser privacy
All AI models run locally (client side) on your hardware, ensuring that your data is processed only on your pc.
Custom memory support
Add custom instructions/memory to allow the AI to provide better and more personalized responses.
OmniBot

Omnibot: Built on the best

Technologies, LLMs and Frameworks

Hugging Face
Hugging Face
Computation tools for building apps using machine learning
Langchain
Langchain
Framework that helps facilitate integration of LLMs into apps
WebLLM
WebLLM
High-Performance In-Browser LLM Inference Engine
TypeScript
TypeScript
A superset of JavaScript that enhances code maintainability.
Next.js
Next.js
Built on a foundation of fast, production-grade tooling
Meta
Meta
Open-source & multilingual Artificial Intelligence models
Microsoft
Microsoft
A family of powerful, small language models (SLMs)

Info Session

Some important information about the omnibot usage

blog image

To run models efficiently, you need a GPU with enough memory. 7B models require 6GB, 3B models require 3GB.

8/12/2024

blog image

If your mobile phone supports WebGl, you'll be able to use Omnibot just as you would on a PC

4/16/2024

blog image

You can eamlessly generate and save your chat messages in either json or markdown format.

6/14/2024

Frequently Asked Questions (FAQs)