Skip to content

πŸ’¬ Responsive personal AI application powered by GPT-4 and beyond, with AI personas, AGI functions, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy and gift #big-AGI-energy! Using Next.js, React, Joy.

License

Notifications You must be signed in to change notification settings

springtian1982/big-agi

Β 
Β 

Repository files navigation

BIG-AGI πŸ€–πŸ’¬

Welcome to big-AGI, FKA nextjs-chatgpt-app. πŸ‘‹πŸŽ‰ Personal AGI App, powered by OpenAI GPT-4 and beyond. Designed for smart humans and super-heroes, this responsive web app comes with Personas, Drawing, Code Execution, PDF imports, Voice support, data Rendering, AGI functions, chats and more. Show your friends some #big-AGI-energy πŸš€

Official Website

Or fork & run on Vercel

Deploy with Vercel

Useful πŸ‘Š

Ask away, paste a ton, copy the gems

  • Engaging AI Personas
  • Clean UX, w/ tokens counters
  • Privacy: user-owned API keys and localStorage
  • Human I/O: Advanced voice support (TTS, STT)
  • Machine I/O: PDF import & Summarization, code execution
  • Many more updates & integrations: ElevenLabs, Helicone, Paste.gg, Prodia
  • Coming up: automatic-AGI reasoning

Support πŸ™Œ

Official Discord


Latest Drops πŸš€

🚨 April: more #big-agi-energy

  • πŸŽ‰ Google Search active in ReAct - add your keys to Settings > Google Search
  • πŸŽ‰ Reason+Act preview feature - activate with 2-taps on the 'Chat' button
  • πŸŽ‰ Image Generation using Prodia (BYO Keys) - /imagine - or menu option
  • πŸŽ‰ Voice Synthesis πŸ“£ with ElevenLabs, including selection of custom voices
  • πŸŽ‰ Precise Token Counter πŸ“ˆ extra-useful to pack the context window
  • πŸŽ‰ Install Mobile APP πŸ“² looks like native (@harlanlewis)
  • πŸŽ‰ UI language with auto-detect, and future app language! (@tbodyston)
  • πŸŽ‰ PDF Summarization 🧩🀯 - ask questions to a PDF! (@fredliubojin)
  • πŸŽ‰ Code Execution: Codepen/Replit πŸ’» (@harlanlewis)
  • πŸŽ‰ SVG Drawing - draw with AI 🎨
  • πŸŽ‰ Chats: multiple chats, AI titles, Import/Export, Selection mode
  • πŸŽ‰ Rendering: Markdown, SVG, improved Code blocks
  • πŸŽ‰ Integrations: OpenAI organization ID
  • πŸŽ‰ Cloudflare deployment instructions, awesome-agi
  • πŸŽ‰ Typing Avatars ⌨️

March: first release

  • πŸŽ‰ AI Personas - including Code, Science, Corporate, and Chat 🎭
  • πŸŽ‰ Privacy: user-owned API keys πŸ”‘ and localStorage πŸ›‘οΈ
  • πŸŽ‰ Context - Attach or Drag & Drop files to add them to the prompt πŸ“
  • πŸŽ‰ Syntax highlighting - for multiple languages 🌈
  • πŸŽ‰ Code Execution: Sandpack - now on branch variant-code-execution
  • πŸŽ‰ Chat with GPT-4 and 3.5 Turbo πŸ§ πŸ’¨
  • πŸŽ‰ Real-time streaming of AI responses ⚑
  • πŸŽ‰ Voice Input πŸŽ™οΈ - works great on Chrome / Windows
  • πŸŽ‰ Integration: Paste.gg integration for chat sharing πŸ“₯
  • πŸŽ‰ Integration: Helicone integration for API observability πŸ“Š
  • πŸŒ™ Dark model - Wide mode β›Ά

Why this? πŸ’‘

Because the official Chat lacks important features, is more limited than the api, at times slow or unavailable, and you cannot deploy it yourself, remix it, add features, or share it with your friends. Our users report that big-AGI is faster, more reliable, and features rich with features that matter to them.

Much features, so fun

Docker 🐳

Pre-built image

Add your OpenAI API key to the .env file, then in a terminal run:

docker-compose up

Locally built image

If you wish to build the image yourself, run

docker build -t big-agi .
docker run --detach 'big-agi'

Code 🧩

TypeScript React Next.js

Clone this repo, install the dependencies, and run the development server:

git clone https://github.com/enricoros/big-agi.git
cd big-agi
npm install
npm run dev

Now the app should be running on http://localhost:3000

Integrations:

  • ElevenLabs Voice Synthesis (bring your own voice too) - Settings > Text To Speech
  • Helicone LLM Observability Platform - Settings > Advanced > API Host: 'oai.hconeai.com'
  • Paste.gg Paste Sharing - Chat Menu > Share via paste.gg
  • Prodia Image Generation - Settings > Image Generation > Api Key & Model

This project is licensed under the MIT License.

GitHub stars GitHub forks GitHub pull requests License

Made with πŸ’™

About

πŸ’¬ Responsive personal AI application powered by GPT-4 and beyond, with AI personas, AGI functions, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy and gift #big-AGI-energy! Using Next.js, React, Joy.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • TypeScript 92.0%
  • CSS 7.5%
  • Other 0.5%