Back to corpus
architecturetechnical paper candidatescore 62

Unified RAG++ Architecture

1. [System Overview](#1-system-overview) 2. [Layer Architecture](#2-layer-architecture) 3. [Foundation Layer: Rust Core](#3-foundation-layer-rust-core) 4. [Data Layer: Supabase Schema](#4-data-layer-supabase-schema) 5. [Ingestion Layer: Prompt Pipeline](#5-ingestion-layer-prompt-pipeline) 6. [ML Layer: CognitiveTwin](#6-ml-layer-cognitivetwin) 7. [Orchestration Layer: Orbit](#7-orchestration-layer-orbit) 8. [Integration Layer: Prompt Logger](#8-integration-layer-prompt-logger) 9. [API Layer: Endpoints Reference](#9

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

1. [System Overview](#1-system-overview) 2. [Layer Architecture](#2-layer-architecture) 3. [Foundation Layer: Rust Core](#3-foundation-layer-rust-core) 4. [Data Layer: Supabase Schema](#4-data-layer-supabase-schema) 5. [Ingestion Layer: Prompt Pipeline](#5-ingestion-layer-prompt-pipeline) 6. [ML Layer: CognitiveTwin](#6-ml-layer-cognitivetwin) 7. [Orchestration Layer: Orbit](#7-orchestration-layer-orbit) 8. [Integration Layer: Prompt Logger](#8-integration-layer-prompt-logger) 9. [API Layer: Endpoints Reference](#9-api-layer-endpoints-reference) 10. [Data Flow Diagrams](#10-data-flow-diagrams) 11. [Configuration Reference](#11-configuration-reference) 12. [Component Interfaces](#12-component-interfaces) - Captures every AI interaction (Claude, ChatGPT, Cursor) as unified `memory_turns` - Computes trajectory coordinates using the Rust core (HNSWIndex + IRCPPropagator) - Trains a CognitiveTwin to learn user reasoning patterns and style - Enables trajectory-aware retrieval for contextual generation | Principle | Implementation | |-----------|----------------| | **Unified Data** | All prompts become `memory_turns` - single source of truth | | **Rust Performance** | Trajectory computation via PyO3 bindings | | **Orbit Orchestration** | Full control over training, context, and fabric operations | | **Global Style** | One evolving signature across all projects | | Layer | Components | Responsibility | |-------|------------|----------------| | **L0: Foundation** | Rust Core, PyO3 Bindings | High-performance vector ops, trajectory computation | | **L1: Data** | Supabase, PostgreSQL, pgvector | Persistent storage, vector search | | **L2: Ingestion** | PromptIngester, Embedder | Transform prompts → memory_turns | | **L3: ML** | CognitiveTwin, HybridTrainer | Learn user patterns, style extraction | | **L4: Orchestration** | Orbit Server | Project management, training triggers | | **L5: Integration** | Prompt Logger, MCP Server | Capture from AI tools, expose to agents | - **HNSWIndex**: Hierarchical Navigable Small World graph for approximate nearest neighbor search - **IRCPPropagator**: Inverse Reasoning Coordinate Propagator for attention computation - **TrajectoryCoordinate5D**: 5-dimensional coordinate system for conversation topology

Promotion decision

What has to happen next

Promote into a technical note or architecture paper with implementation anchors.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.