OvidijusParsiunas/deep-chat

Fully customizable AI chatbot component for your website

What it solves

Deep Chat provides a ready-to-use, highly customizable AI chat component that developers can embed into websites with a single line of code, eliminating the need to build a chat interface from scratch when integrating AI services.

How it works

It acts as a frontend UI component that can be connected to AI backends in three primary ways:

  1. Direct Connection: Connects directly to popular AI APIs (like OpenAI or Claude) from the browser for prototyping.
  2. Custom API: Connects to a custom server via a defined request property.
  3. Web Model: Hosts an LLM entirely within the browser using the deep-chat-web-llm module, removing the need for a server entirely.

Who it’s for

Web developers who want to quickly add an AI chatbot to their site using any major UI framework (React, Vue, Svelte, Angular, Solid, etc.) or vanilla JavaScript.

Highlights

  • Multimodal Input: Supports sending/receiving files, capturing photos via webcam, and recording audio via microphone.
  • Speech Capabilities: Includes built-in Speech-to-Text for input and Text-to-Speech for responses, as well as support for Speech-to-Speech models.
  • Broad Integration: Direct browser-side connection to over 20 popular AI APIs.
  • Rich Text Support: Renders Markdown and custom elements for structured text and code.
  • Flexible UX: Features a "Focus mode" for latest messages, local browser storage for session recovery, and fully customizable styling.

Related

  • Project
    Hyk260/PureChat

    A cross-platform chat application and AI development framework that integrates multiple LLMs like OpenAI and DeepSeek with a unified interface.

  • Project
    baptisteArno/typebot.io

    A visual chatbot builder that allows users to create advanced, embeddable chatbots with AI integrations and real-time data collection.

  • Project
    AtomicBot-ai/Atomic-Chat

    Atomic Chat is a desktop/mobile app that runs open‑weight LLMs locally and exposes them via an OpenAI‑compatible HTTP server (`http://localhost:1337/v1`). It supports multiple back‑ends (llama.cpp, a TurboQuant‑enhanced fork, and Apple‑Silicon MLX‑VLM), speculative decoding tricks for speed, cloud‑model fallbacks, and one‑click integration with many open‑source coding agents. The UI handles model download, engine selection, and API routing, making private on‑device inference easy for developers and researchers.

  • Project
    addyosmani/chatty

    A private, in-browser AI chat interface that uses WebGPU to run LLMs locally on your hardware for offline use and data privacy.

  • Project
    alfredfrancis/ai-chatbot-framework

    A self-hosted, low-code Python framework for building AI chatbots with NLU, tool calling, and multi-channel integration.