제품 등급, 현지 최초의 계층 및 신경 영감을 주는 자율 AI 에이전트 (v4.0.0 — “Gomaa Neo”).

Gomaa는 영구적이고 인간적인 행동과 transhuman 장기 기억을 가진 AI 대리인 (Hermes, OpenClaw, Claude 데스크탑, Cursor, 윈드 서핑, CrewAI, LangChain)를 갖추고 있습니다. 그것은 인간의 읽기 가능 Obsidian Markdown Vaults ** 고속 ** PostgreSQL + pgvector (HNSW) ** 또는 Zero-config ** SQLite WAL, 파워 4-Quadrant Cognitive Architecture (Episodic, Semantic, Procedural, Working Memory), **HippoRAG 2 개인화 PageRank (PPR) ** 상호 연관성 검색, ** Retrieval ** (Episodic, Semantic, Procedural, Working Memory), **HippoRAG 2 개인화 PageRank (PPR) ** 상호 작용성 검색, ** Retrieval ** (Epactivic, Retrieventation, Concience)

---

왜 Gomaa인가?

대부분의 AI 메모리 시스템은 세 가지 기본 결함으로 고통:

1. 블랙 박스 Vector Blobs: Memories는 opaque 벡터 데이터베이스로 사라졌습니다. 인간은 감사, 정확하거나, 어떤 대리인이 배운 것을 curate 할 수 없습니다.
2. 명세.

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 ($\ln(1 + \text{access_count})$).