Aura Backend - Advanced AI Companion
About
The Aura Emotion AI system has chroma with a local embedding model, memvid qr code mp4 infinite memory, brainwave and neurochemical simulations, sociobiological reasoning, autonomous subsystem processing with a Gemini flash model so the main model is less taxed, is a MCP client w
Explore
- Real-time Reasoning Capture: Extract and analyze AI thought processes during conversations
- Thought Summarization: Automatic generation of reasoning summaries for quick understanding
- Cognitive Transparency: Full visibility into how Aura approaches problems and makes decisions
- Reasoning Metrics: Detailed analytics on thinking patterns, processing time, and cognitive load
ENABLE_EMOTIONAL_ANALYSIS=true
ENABLE_COGNITIVE_TRACKING=true
ENABLE_VECTOR_SEARCH=true
ENABLE_FILE_EXPORTS=true
```
cd aura_backend
python test_thinking.py
- [ ] Real-time WebSocket connections
- [ ] Advanced emotion prediction models
- [ ] Multi-user collaboration features
- [ ] Enhanced MCP tool ecosystem
- [ ] Mobile app backend support
- [ ] Advanced analytics dashboard
- [ ] Integration with external AI models
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Aura Backend - Advanced AI CompanionCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.12+
- Google API Key (from Google AI Studio)
- At least 4GB RAM (for vector embeddings)
- 2GB+ storage space
- Thinking Budget: Configurable reasoning depth (1024-32768 tokens)
- Response Integration: Optional inclusion of reasoning in user responses
- Pattern Analysis: Long-term analysis of reasoning patterns and cognitive development
- Performance Optimization: Thinking efficiency metrics and optimization recommendations
GEMINI_API_KEY=your-gemini-api-key-here
CHROMA_PERSIST_DIRECTORY=./aura_chroma_db
AURA_DATA_DIRECTORY=./aura_data
ENABLE_EMOTIONAL_ANALYSIS=true
ENABLE_COGNITIVE_TRACKING=true
ENABLE_VECTOR_SEARCH=true
ENABLE_FILE_EXPORTS=true
Easy Full System Start: This will start both backend and frontend in separate terminals automatically:
./start_full_system.sh
This script will:
- ✅ Check all prerequisites (Node.js, npm, uv)
- ✅ Set up project environment (.venv with Python 3.12 at root)
- ✅ Install frontend dependencies if needed
- ✅ Start backend in one terminal (with hot reload)
- ✅ Start frontend in another terminal (with hot reload)
- ✅ Verify both services are running
- ✅ Display status and URLs
Stop All Services:
./stop_full_system.sh
To stop all services, you can also run:
fuser -k 8000/tcp && fuser -k 5173/tcp
If you prefer to start services manually:
Backend:
cd aura_backend
./start.sh
Frontend (in a separate terminal):
npm install # First time only
npm run dev
Edit your directory path and place in claude desktop config json.
{
"mcpServers": {
"aura-companion": {
"command": "uv",
"args": [
"--directory",
"/home/ty/Repositories/ai_workspace/emotion_ai/aura_backend",
"run",
"aura_server.py"
]
}
}
}
rm -rf venv/
./setup.sh
2. API Key Issues:
source venv/bin/activate
echo $GOOGLE_API_KEY
3. Vector DB Issues: This is asshole AI- you will lose your db
1. search_aura_memories: Semantic search through conversation history
2. analyze_aura_emotional_patterns: Deep emotional trend analysis
3. store_aura_conversation: Add memories to Aura's knowledge base
4. get_aura_user_profile: Retrieve user personalization data
5. export_aura_user_data: Data export functionality
6. query_aura_emotional_states: Information about emotional intelligence system
7. query_aura_aseke_framework: ASEKE cognitive architecture details
To connect external MCP clients to Aura:
Create custom MCP tools by extending the mcp_server.py:
```python
@tool
async def custom_aura_tool(params: CustomParams) -> Dict[str, Any]:
"""Your custom tool implementation"""
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"aura backend - advanced ai companion": {
"emotion_ai": {
"command": "uv",
"args": [
"venv",
"--python",
"3.12"
]
}
}
}
}McpServers
{
"emotion_ai": {
"command": "uv",
"args": [
"venv",
"--python",
"3.12"
]
}
}
> Sophisticated AI Companion with Vector Database, Emotional Intelligence, and Model Context Protocol Integration
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
