Continuo Memory System

# Continuo Memory System - Examples This directory contains example scripts demonstrating the Continuo Memory System capabilities. ## 📁 Available Examples ### `memory/` - Memory System Examples - **[basic_usage.py](memory/basic_usage.py)** - Basic memory storage and retrieval - **[hierarchical_demo.py](memory/hierarchical_demo.py)** - Hierarchical compression (N0 → N1 → N2) - **[complete_demo.py](memory/complete_demo.py)** - Complete workflow demonstration - **[auto_mode_demo.py](memory/auto_mode_demo.py)** - Autonomous agent with persistent memory ## 🚀 Running Examples ### Prerequisites Make sure you've set up the memory system first: ```bash # Run setup script ./scripts/setup_memory.sh # Activate virtual environment source venv_memory/bin/activate ``` ### Basic Usage ```bash # Store and retrieve memories python examples/memory/basic_usage.py # Test hierarchical compression python examples/memory/hierarchical_demo.py # Run autonomous agent demo python examples/memory/auto_mode_demo.py ``` ### With MCP Server ```bash # Start the MCP server ./scripts/run_memory_server.sh # Or manually python src/mcp/memory/mcp_memory_server.py --provider local --db-path ./test_db ``` ## 📖 Learning Path 1. **Start with `basic_usage.py`** - Understand core concepts 2. **Explore `hierarchical_demo.py`** - See compression in action 3. **Run `complete_demo.py`** - Full system demonstration 4. **Try `auto_mode_demo.py`** - Autonomous agent capabilities ## 🔧 Configuration ### Local Embeddings (Free) Uses `sentence-transformers` with local models: ```python python examples/memory/basic_usage.py # No API keys needed! ``` ### OpenAI Embeddings (Optional) Set your API key: ```bash export OPENAI_API_KEY="your-key-here" python src/mcp/memory/mcp_memory_server.py --provider openai ``` ## 💡 Key Concepts Demonstrated - **Semantic Search** - Find relevant information by meaning - **Hierarchical Compression** - Automatic summarization (N0 → N1 → N2) - **Persistent Storage** - ChromaDB vector database - **MCP Integration** - Use with Qoder/Cursor IDEs - **Autonomous Agents** - Self-directed memory management ## 🐛 Troubleshooting **Import errors?** ```bash # Make sure virtual environment is activated source venv_memory/bin/activate # Install dependencies pip install -r requirements.txt ``` **Database issues?** ```bash # Clear test database rm -rf test_db/ rm -rf example_chroma_db/ # Re-run example python examples/memory/basic_usage.py ``` **Model download slow?** - First run downloads ~80MB model - Model cached in `~/.cache/torch/` - Subsequent runs are instant ## 📚 Documentation - See [SETUP.md](../SETUP.md) for installation - See [continuo.markdown](../continuo.markdown) for architecture details - See [README.md](../README.md) for project overview --- **Questions?** Open an issue or check the main documentation!