intelligentnode/IntelliChat

Modern AI chatbot supporting multiple LLMs. Switch between Gemini, Mistral, Llama, Claude and ChatGPT.

TypeScript

60

244 commits

updated Sep 18, 2026

See the code

See what people are saying (1)

README

IntelliChat

Deploy with Vercel Open in GitHub Codespaces

IntelliChat is an open-source AI chatbot built with IntelliNode and Next.js. It is designed to accelerate the integration of multiple language models into chatbot apps.

https://github.com/intelligentnode/IntelliChat/assets/2751950/47d7db12-e299-449f-9351-39185c659d84

Features

  • Select your preferred AI Provider and model from the UI.
    • OpenAI: GPT-5.5, GPT-5.5 Pro, GPT-5.4, GPT-5.1, GPT-4.1.
    • Anthropic: Claude Sonnet 5, Opus 5, Fable 5.1, Haiku 4.5.
    • Google Gemini: Gemini 3.6, 3.7 and 3.8 Flash, 3.1 Pro.
    • Cohere: Command A Plus, Command A, Command A Reasoning, Command R.
    • Mistral AI: Mistral Medium, Mistral Small, Magistral, Ministral.
    • Azure OpenAI.
    • Replicate: Llama chat models.
    • OpenRouter, Groq and DeepSeek: OpenAI-compatible APIs.
    • Ollama, LM Studio and vLLM: local and self-hosted models.
  • Stream replies and stop them at any time.
  • Generate images with the image button or /image.
  • Attach an image and ask about it.
  • Dictate messages with the microphone and listen to replies.
  • Write in any language, including Frensh, Spanish, Arabic.
  • Code blocks with highlighting, file names, copy and download.
  • Paste a GitHub link to ask about a repo, file, issue or pull request.
  • Connect a GitHub repo, or a local folder when running locally, and the assistant reads the code, checks issues and shows each step.
  • Use the keys in .env or add your own in the settings, with separate keys for chat, images and voice.
Streaming chatImage generation
Streaming reply with the Stop buttonGenerated image with a download button
Ask about an imageVoice
Question about an attached imageDictated question with the reply read aloud
Multi-lang chat (Arabic)Multi-lang image prompt
Arabic question and reply written right to leftImage generated from an Arabic prompt
GitHub repoLocal file edit
The assistant reading a connected GitHub repo step by stepThe assistant fixing a local file and showing the diff
SettingsLocal models
Settings panel using a key from .envOllama models loaded from the local server

Installing and Running the App

  1. cd intellichat.
  2. Install the dependencies: pnpm install or npm install or yarn install.
  3. Optional: copy .env.example to .env and add your keys. Keys can also be added from the settings.
  4. Start the Next.js server pnpm dev or npm run dev or yarn dev.

Open http://localhost:3000 with your browser to see the result.



Built with: Intellinode, Next.js, Shadcn, and TailwindCSS.

anthropic
azure-openai
chatbot
chatbots
chatbot-ui
chatgpt
claude
claude-code
fable
gemini
llm
mistral
openai
opengpt
replicate
typescript
vercel
vllm

Contributors

Eytyy

132 commits

Barqawiz

72 commits

intelligentnode

36 commits

Niralempiric

3 commits

intelligentnode/IntelliChat

Modern AI chatbot supporting multiple LLMs. Switch between Gemini, Mistral, Llama, Claude and ChatGPT.

TypeScript

60

244 commits

updated Sep 18, 2026

See the code

See what people are saying (1)

README

IntelliChat

Deploy with Vercel Open in GitHub Codespaces

IntelliChat is an open-source AI chatbot built with IntelliNode and Next.js. It is designed to accelerate the integration of multiple language models into chatbot apps.

https://github.com/intelligentnode/IntelliChat/assets/2751950/47d7db12-e299-449f-9351-39185c659d84

Features

  • Select your preferred AI Provider and model from the UI.
    • OpenAI: GPT-5.5, GPT-5.5 Pro, GPT-5.4, GPT-5.1, GPT-4.1.
    • Anthropic: Claude Sonnet 5, Opus 5, Fable 5.1, Haiku 4.5.
    • Google Gemini: Gemini 3.6, 3.7 and 3.8 Flash, 3.1 Pro.
    • Cohere: Command A Plus, Command A, Command A Reasoning, Command R.
    • Mistral AI: Mistral Medium, Mistral Small, Magistral, Ministral.
    • Azure OpenAI.
    • Replicate: Llama chat models.
    • OpenRouter, Groq and DeepSeek: OpenAI-compatible APIs.
    • Ollama, LM Studio and vLLM: local and self-hosted models.
  • Stream replies and stop them at any time.
  • Generate images with the image button or /image.
  • Attach an image and ask about it.
  • Dictate messages with the microphone and listen to replies.
  • Write in any language, including Frensh, Spanish, Arabic.
  • Code blocks with highlighting, file names, copy and download.
  • Paste a GitHub link to ask about a repo, file, issue or pull request.
  • Connect a GitHub repo, or a local folder when running locally, and the assistant reads the code, checks issues and shows each step.
  • Use the keys in .env or add your own in the settings, with separate keys for chat, images and voice.
Streaming chatImage generation
Streaming reply with the Stop buttonGenerated image with a download button
Ask about an imageVoice
Question about an attached imageDictated question with the reply read aloud
Multi-lang chat (Arabic)Multi-lang image prompt
Arabic question and reply written right to leftImage generated from an Arabic prompt
GitHub repoLocal file edit
The assistant reading a connected GitHub repo step by stepThe assistant fixing a local file and showing the diff
SettingsLocal models
Settings panel using a key from .envOllama models loaded from the local server

Installing and Running the App

  1. cd intellichat.
  2. Install the dependencies: pnpm install or npm install or yarn install.
  3. Optional: copy .env.example to .env and add your keys. Keys can also be added from the settings.
  4. Start the Next.js server pnpm dev or npm run dev or yarn dev.

Open http://localhost:3000 with your browser to see the result.



Built with: Intellinode, Next.js, Shadcn, and TailwindCSS.

anthropic
azure-openai
chatbot
chatbots
chatbot-ui
chatgpt
claude
claude-code
fable
gemini
llm
mistral
openai
opengpt
replicate
typescript
vercel
vllm

Contributors

Eytyy

132 commits

Barqawiz

72 commits

intelligentnode

36 commits

Niralempiric

3 commits

Languages

TypeScript

97.5%

JavaScript

1.2%