Welcome to big-AGI
👋 your personal AGI application
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 much more. Comes with plenty of #big-AGI-energy
🚀
Or fork & run on Vercel
- AI Personas
- Polished UI: installable web app, mobile-friendly, token counters, etc.
- Fast UX: Microphone, Camera OCR, Drag files, Voice Synthesis
- Models: OpenAI, Anthropic, Azure, OpenRouter, Local models, and more
- Private: use your own API keys and self-host if you like
- Advanced: PDF import & Summarization, code execution
- Integrations: ElevenLabs, Helicone, Paste.gg, Prodia and more
- Enjoy the hosted open-source app on big-AGI.com
- Chat with us
- Deploy your fork for your friends and family
- send PRs! ... 🎭Editing Personas, 🧩Reasoning Systems, 🌐Community Templates, and your big-IDEAs
- Cloudflare API Gateway support
- Helicone for Anthropic support
- Text Tools - incl. highlight differences
- Expanded Model Support: Azure and OpenRouter models, including gpt-4-32k
- Share and clone conversations with public links
- Removed the 20 chats hard limit (Ashesh3)
- Latex Rendering
- Augmented Chat modes (Labs)
- Camera OCR - real-world AI - take a picture of a text, and chat with it
- Anthropic models support, e.g. Claude
- Backup/Restore - save chats, and restore them later
- Local model support with Oobabooga server - run your own LLMs!
- Flatten conversations - conversations summarizer with 4 modes
- Fork conversations - create a new chat, to experiment with different endings
- New commands: /s to add a System message, and /a for an Assistant message
- New Chat modes: Write-only - just appends the message, without assistant response
- Fix STOP generation - in sync with the Vercel team to fix a long-standing NextJS issue
- Fixes on the HTML block - particularly useful to see error pages
- New OpenAI Models support - 0613 models, including 16k and 32k
- Cleaner UI - with rationalized Settings, Modals, and Configurators
- Dynamic Models Configurator - easy connection with different model vendors
- Multiple Model Vendors Support framework to support many LLM vendors
- Per-model Options (temperature, tokens, etc.) for fine-tuning AI behavior to your needs
- Support for GPT-4-32k
- Improved Dialogs and Messages
- Much Enhanced DX: TRPC integration, modularization, pluggable UI, etc
- Google Search active in ReAct - add your keys to Settings > Google Search
- Reason+Act preview feature - activate with 2-taps on the 'Chat' button
- Image Generation using Prodia (BYO Keys) - /imagine - or menu option
- Voice Synthesis 📣 with ElevenLabs, including selection of custom voices
- Precise Token Counter 📈 extra-useful to pack the context window
- Install Mobile APP 📲 looks like native (@harlanlewis)
- UI language with auto-detect, and future app language! (@tbodyston)
- PDF Summarization 🧩🤯 - ask questions to a PDF! (@fredliubojin)
- Code Execution: Codepen/Replit 💻 (@harlanlewis)
- SVG Drawing - draw with AI 🎨
- Chats: multiple chats, AI titles, Import/Export, Selection mode
- Rendering: Markdown, SVG, improved Code blocks
- Integrations: OpenAI organization ID
- Cloudflare deployment instructions, awesome-agi
- Typing Avatars ⌨️
- AI Personas - including Code, Science, Corporate, and Chat 🎭
- Privacy: user-owned API keys 🔑 and localStorage 🛡️
- Context - Attach or Drag & Drop files to add them to the prompt 📁
- Syntax highlighting - for multiple languages 🌈
- Code Execution: Sandpack -
now on branch
variant-code-execution
- Chat with GPT-4 and 3.5 Turbo 🧠💨
- Real-time streaming of AI responses ⚡
- Voice Input 🎙️ - works great on Chrome / Windows
- Integration: Paste.gg integration for chat sharing 📥
- Integration: Helicone integration for API observability 📊
- 🌙 Dark model - Wide mode ⛶
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.
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
- ElevenLabs Voice Synthesis (bring your own voice too) - Settings > Text To Speech
- Helicone LLM Observability Platform - Models > OpenAI > 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
For more detailed information on deploying with Docker, please refer to the docker deployment documentation.
Firstly, write all your API keys and env vars to an
.env
file, and make sure the env file is using both build and run. See docs/environment-variables.md for a list of all environment variables.
```bash
docker build -t big-agi .
docker run --detach 'big-agi'
Warning: the UI will still be asking for keys, as the image was built without the API keys
docker-compose up
Please refer to the Cloudflare deployment documentation.
Create your GitHub fork, create a Vercel project over that fork, and deploy it. Or press the button below for convenience.
This project is licensed under the MIT License.
Made with 💙