Awaken Intelligence. Automate Workflows. Empower Creation.
An advanced multi-agent AI platform for transformative personal and professional growth.
S.A.T.O.R.I. AI (System for Agentic Tasks, Orchestration, and Real-time Intelligence) is a cutting-edge AI platform that harmonizes advanced technology with human-centric design. By leveraging multiple specialized AI agents, it creates a synergistic environment for personal growth, workflow optimization, and knowledge management.
- Personal Growth: Guide your journey of self-discovery and development
- Workflow Mastery: Optimize and automate your professional processes
- Knowledge Synthesis: Transform information into actionable insights
- Strategic Vision: Develop clear pathways to achieve your goals
- Voice Interaction: Natural two-way voice communication with AI agents
- Dynamic framework powered by LangGraph and LangChain
- Specialized agents for different domains:
- π§ββοΈ Discovery Agent: Personal growth and self-reflection
- β‘ Task Agent: Workflow optimization and automation
- π Knowledge Agent: Information management and retrieval
- π― Mentor Agent: Strategic guidance and planning
- π€ Voice Agent: Natural voice interactions and processing
- Bidirectional voice communication:
- Real-time speech-to-text using Deepgram
- Text-to-speech synthesis using Eleven Labs
- Multiple voice interaction modes:
- Live voice conversations
- Voice note messaging
- Voice command processing
- Advanced voice features:
- Real-time transcription
- Multiple language support
- Voice activity detection
- Smart punctuation and formatting
- Voice customization:
- Multiple voice options
- Stability and clarity control
- Style and emotion adjustment
- Speaker boost enhancement
- Audio management:
- Voice recording and playback
- Audio file processing
- Download and sharing options
- Advanced document understanding and analysis
- Context-aware responses and recommendations
- Real-time learning and adaptation
- Memory management and knowledge retention
- Voice response generation
- Text, voice, and visual input processing
- Rich interactive responses
- Dynamic visualization of insights
- Adaptive user interfaces
- Voice output customization
- Vector-based information storage
- Semantic search and retrieval
- Automated knowledge organization
- Contextual recommendations
- Backend: FastAPI, LangChain, LangGraph
- Frontend: Streamlit (POC phase)
- Database: ChromaDB, PostgreSQL with pgvector
- AI Models: OpenAI GPT-4, Ada Embeddings
- Voice:
- Speech-to-Text: Deepgram Nova-2
- Text-to-Speech: Eleven Labs
- Audio Processing: PyAudio
graph TD
A[User Interface] -->|Requests| B[API Layer]
B -->|Processing| C[Core AI System]
C -->|Storage| D[Database Layer]
B -->|Voice| E[Voice Service]
subgraph "Core AI System"
C1[Discovery Agent]
C2[Task Agent]
C3[Knowledge Agent]
C4[Mentor Agent]
end
subgraph "Voice Processing"
E1[Text-to-Speech]
E2[Voice Settings]
E3[Audio Management]
end
C --> C1
C --> C2
C --> C3
C --> C4
E --> E1
E --> E2
E --> E3
- Python 3.10+
- PostgreSQL 14+ with pgvector extension
- OpenAI API key
- Eleven Labs API key
- Node.js 18+ (for development)
- Clone the repository
git clone https://github.com/yourusername/SATORI-AI.git
cd SATORI-AI
- Create and activate virtual environment
# Windows
python -m venv venv
.\venv\Scripts\activate
# Linux/MacOS
python -m venv venv
source venv/bin/activate
- Install dependencies
pip install -r requirements.txt
- Configure environment variables
cp .env.example .env
# Edit .env with your settings:
# - OPENAI_API_KEY
# - ELEVEN_LABS_API_KEY
# - Other configuration options
- Initialize database
# Install pgvector extension
psql -d your_database -c 'CREATE EXTENSION vector;'
# Run migrations
python scripts/init_db.py
- Start the backend server
python run.py
# or
uvicorn backend.api.main:app --reload
- Start the frontend application
streamlit run frontend/app.py
The application will be available at:
- Frontend: http://localhost:8501
- Backend API: http://localhost:8000
- API Documentation: http://localhost:8000/docs
-
Access Voice Settings
- Open the Voice Settings panel in the UI
- Select your preferred voice
- Adjust voice parameters:
- Stability (0-1)
- Style (0-1)
- Similarity Boost (0-1)
- Speaker Boost (on/off)
-
Enable Voice Responses
- Toggle voice response in chat interface
- Customize voice per conversation
- Download or share generated audio
- Interactive API documentation is available at
/docs
when running the server - OpenAPI specification available at
/openapi.json
- Install development dependencies
pip install -r requirements-dev.txt
- Set up pre-commit hooks
pre-commit install
- Run tests
pytest
- Formatting:
black .
- Linting:
flake8
- Type checking:
mypy .
- Sort imports:
isort .
main
: Production-ready codedevelop
: Development branch- Feature branches:
feature/*
- Bug fixes:
fix/*
- Releases:
release/*
We welcome contributions! Please see our Contributing Guidelines for details on:
- Code of Conduct
- Development process
- Pull request process
- Coding standards
- Testing requirements
This project is licensed under the MIT License - see the LICENSE file for details.
- Built with β€οΈ and powered by @hams_ollo
- Inspired by the Zen concept of Satori - sudden enlightenment
- Special thanks to all contributors
Website β’ Documentation β’ Report Bug β’ Request Feature β’ Security