** Иерархический и нейро-вдохновленный механизм когнитивной памяти для автономных агентов ИИ (v4.0.0 — «Gomaa Neo»).

Gomaa оснащает агентов ИИ (Hermes, OpenClaw, Claude Desktop, Cursor, Windsurf, CrewAI, LangChain) постоянной, человекоподобной и трансчеловеческой долговременной памятью. Он объединяет считываемые человеком Obsidian Markdown Vaults с высокоскоростным PostgreSQL + pgvector (HNSW) или нулевой конфигурацией SQLite WAL, питая 4-Quadrant Cognitive Architecture (Episodic, Semantic, Procedural, Working Memory), HippoRAG 2 Personalized PageRank (PPR) ассоциативное извлечение, *3-Phase Biological Sleep Consolidation (SWS + REM + Synaptic Homeostasis), ACT-R Base-Level Activation, Hybrid Reciprocal Rank Fusion (RRF) Search, Ebbinghaus temporal decay, cross-agent fleet sharing и асинхронную облачную синхронизацию Google Drive.

Почему Гомаа?

Большинство систем памяти ИИ страдают от трех фундаментальных недостатков:

1. ** Black-Box Vector Blobs: ** Воспоминания исчезают в непрозрачных векторных базах данных. Люди не могут проверять, исправлять или курировать то, что узнал агент.

Gomaa 🧠

Production-grade, local-first hierarchical & neuro-inspired cognitive memory engine for autonomous AI agents (v4.0.0 — “Gomaa Neo”).

Gomaa equips AI agents (Hermes, OpenClaw, Claude Desktop, Cursor, Windsurf, CrewAI, LangChain) with permanent, human-like and transhuman long-term memory. It unites human-readable Obsidian Markdown Vaults with high-speed PostgreSQL + pgvector (HNSW) or zero-config SQLite WAL, powering a 4-Quadrant Cognitive Architecture (Episodic, Semantic, Procedural, Working Memory), HippoRAG 2 Personalized PageRank (PPR) associative retrieval, 3-Phase Biological Sleep Consolidation (SWS + REM + Synaptic Homeostasis), ACT-R Base-Level Activation, hybrid Reciprocal Rank Fusion (RRF) search, Ebbinghaus temporal decay, cross-agent fleet sharing, and asynchronous Google Drive cloud synchronization.

---

💡 Why Gomaa?

Most AI memory systems suffer from three fundamental flaws:

1. Black-Box Vector Blobs: Memories disappear into opaque vector databases. Humans cannot audit, correct, or curate what the agent learned.
2. Context Pollution & Flat Storage: Raw chat logs, factual knowledge, and procedural skills are dumped into a single flat vector index without forgetting mechanisms or cognitive separation.
3. Multi-Hop Blindness & Domain Cross-Contamination: Standard vector similarity fails when connecting facts across multiple hops, while un-scoped stores leak context across domains.

Gomaa v4.0 (“Gomaa Neo”) solves this:

• 🧠 4-Quadrant Cognitive Architecture: Explicit separation of Episodic (episodic_events turn ledger), Semantic (notes + weighted links), Procedural (procedural_playbooks with Bayesian Laplace utility), and Working Memory (working_memory bounded by Miller’s Law $7 \pm 2$).
• 🕸️ HippoRAG 2 Associative PPR Retrieval: Single-step multi-hop retrieval using Personalized PageRank ($K=20, \alpha=0.15$) over bi-directional weighted graph links, fused with dense vectors, BM25 FTS, and ACT-R base-level activation ($\ln(1 + \text{access_count})$).