RAG++ (Retrieval-Augmented Generation Plus Plus)

RAG++ is TrajectoryOS's state-based retrieval and policy recommendation system. Unlike traditional RAG which retrieves "relevant chunks," RAG++ retrieves **successful state transitions** from similar life regimes and recommends actions based on what worked in the past. | Aspect | Traditional RAG | TrajectoryOS RAG++ | |--------|----------------|-------------------| | **Unit of Retrieval** | Text chunks | State transitions (events-as-nodes-in-life-graph) | | **Relevance** | Semantic similarity | Semantic + topological + dynamical state + phase | | **What It Returns** | Documents/passages | Successful transitions with action patterns | | **Generator Output** | Summarize/Answer | Strategic intervention recommendations | | **Geometry** | 1D (semantic) | 3D (topological + temporal + dynamical) | ### 1. State Estimator ([StateEstimator.ts](../../services/trajectory-core/src/services/StateEstimator.ts)) **Key Functions**: - `estimateState()` - Physics → CurrentState - `compareStates()` - Similarity scoring (0-1) - `computeTimeOfDay()` - Extract phase from timestamp ### 2. Action Classifier ([ActionClassifier.ts](../../services/trajectory-core/src/services/ActionClassifier.ts))