# synaptic-memory

> Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.

- **URL**: https://www.freshcrate.ai/projects/synaptic-memory
- **Author**: PlateerLab
- **Category**: MCP Servers
- **Latest version**: `v0.16.0` (2026-04-17)
- **License**: MIT
- **Source**: https://github.com/PlateerLab/synaptic-memory
- **Language**: Python
- **GitHub**: 27 stars, 1 forks
- **Registry**: github
- **Tags**: `ai-agent`, `embedding`, `graph-database`, `hebbian-learning`, `knowledge-graph`, `llm`, `mcp`, `mcp-server`, `python`

## Description

Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.16.0` | 2026-04-17 | High | # Synaptic Memory v0.16.0 — release notes  **Release date**: 2026-04-17 · **License**: MIT · **Install**: `pip install "synaptic-memory[sqlite,korean,vector,mcp]"`  ---  ## TL;DR  v0.16.0 is the cleanup release that makes Synaptic's benchmark numbers match what the SDK actually does. Five changes:  1. **`graph.search()` now defaults to `engine="evidence"`** — the    hybrid BM25 + HNSW + PPR + MMR pipeline that the MCP tool path    already used. Legacy HybridSearch is deprecated and will be    re |
| `v0.13.0` | 2026-04-12 | High | ## Highlights  Major improvements to multi-turn agent search quality on structured data.  ### 🔥 Agent benchmark results  \| Dataset \| Before \| After \| \|---------\|--------\|-------\| \| X2BEE Hard agent \| 1/19 (5%) \| **17/19 (89%)** \| \| assort Hard agent \| 1/15 (7%) \| **12/15 (80%)** \| \| KRRA Hard MRR \| 0.808 \| **1.000** (15/15) \|  ### 🌐 Public benchmarks (EvidenceSearch + embed + reranker)  \| Dataset \| Before \| After \| \|---------\|--------\|-------\| \| HotPotQA-24 \| 0.727 \| **0.964** \| \| Allganize RA |
| `v0.9.0` | 2026-03-23 | Medium | ## Synaptic Memory v0.9.0  ### Core Improvements - **BM25 hybrid scoring** — corpus-size adaptive (large: BM25 80%, small: substring 70%) - **Supersede detection** — same-title nodes prefer newest (by updated_at) - **Auto-chunking API** — `add_document(chunk_size=1000)` with sentence-boundary splitting + PART_OF edges - **PPR edge type weights** — CAUSED 1.0 > RELATED 0.4 (reduces noise from S2 ablation -14~-32%) - **Kind soft boost** — hard filter → 1.5x score boost (MRR +9%) - **Phrase node fi |
| `v0.8.0` | 2026-03-22 | Low | ## Summary  Graph API expansion release addressing 5 user feedback items: full node listing, partial updates, unified maintenance, conversation session management, and custom NodeKind support.  ## New Features  ### `graph.list()` — List all nodes ```python nodes = await graph.list()                          # all lessons = await graph.list(kind=NodeKind.LESSON)     # filter by kind recent = await graph.list(limit=10)                  # with limit ```  ### `graph.update()` — Partial node update ` |
| `v0.7.0` | 2026-03-22 | Low | ## Synaptic Memory v0.7.0 — PPR, Evidence Chain, Auto-Ontology 최적화, HotPotQA 0.856  ### Added - **Evidence Chain Assembly** — small LLM augmentation for multi-hop reasoning, HotPotQA Correctness 0.856 (+9.2%) - **Personalized PageRank (PPR) engine** — replaced spreading activation, multi-hop retrieval +28% - **End-to-end QA benchmark** — HotPotQA 24-question suite for Cognee comparison (Correctness 0.784) - **Auto-ontology optimization** — HybridClassifier, batch LLM processing, EmbeddingRelatio |
| `v0.6.0` | 2026-03-22 | Low | ## Synaptic Memory v0.6.0 — 자동 온톨로지 + 하이브리드 검색 + 벤치마크  ### Added - **Auto-ontology construction** — LLM-based ontology building with search-optimized metadata generation - **LLM classifier prompt optimization** — few-shot examples improved accuracy from 50% to 86% - **FTS + embedding hybrid scoring** — S7 Auto+Embed achieved MRR 0.83 - **Kind/tag/search_keywords utilization** in search — FTS and ranking boost - **Ontology auto-construction + benchmark framework + search engine improvements**  ## |
| `v0.5.0` | 2026-03-22 | Low | ## Synaptic Memory v0.5.0 — 온톨로지 + 에이전트 활동 추적 + Intent 검색 + Neo4j  ### Added - **Ontology Engine** — dynamic type hierarchy, property inheritance, relation constraint validation (`OntologyRegistry`) - **Agent Activity Tracking** — session/tool call/decision/outcome capture (`ActivityTracker`) - **Intent-based Agent Search** — 6 search strategies: similar_decisions, past_failures, related_rules, reasoning_chain, context_explore, general (`AgentSearch`) - **Neo4j Backend** — native Cypher graph tr |
| `v0.4.0` | 2026-03-22 | Low | ## Synaptic Memory v0.4.0 — MCP 서버 (7개 tool) + synaptic-mcp CLI  ### Added - **MCP Server** — 7 tools (knowledge search/add/link/reinforce/stats/export/consolidate) - **SQLite Backend** — FTS5, recursive CTE, WAL mode - **QA Test Suite** — 169 Wikipedia + 368 GitHub real-data verification cases - `synaptic-mcp` CLI entry point |
| `v0.3.0` | 2026-03-22 | Low | ## Synaptic Memory v0.3.0 — 프로토콜 구현체 + LRU 캐시 + JSON export + 노드 병합  ### Added - **Protocol implementations** — LLM QueryRewriter, RegexTagExtractor, EmbeddingProvider - **LRU Cache** — NodeCache with hit rate tracking - **JSON Exporter** — structured JSON export - **Node Merge** — duplicate node merging with edge reconnection - **Find Duplicates** — title similarity-based duplicate detection |
| `v0.2.0` | 2026-03-22 | Low | ## Synaptic Memory v0.2.0 — PostgreSQL 백엔드 + PyPI 준비  ### Added - **PostgreSQL backend** — asyncpg + pgvector HNSW + pg_trgm + recursive CTE - Vector search with cosine distance (pgvector) - Trigram fuzzy matching with graceful ILIKE fallback - Hybrid search: FTS + fuzzy + vector merged results - Connection pooling (asyncpg Pool, min=2, max=10) - Configurable `embedding_dim` parameter - `ResonanceWeights` added to public exports - Configurable consolidation thresholds (TTL, promotion access coun |

## Citation

- HTML: https://www.freshcrate.ai/projects/synaptic-memory
- Markdown: https://www.freshcrate.ai/projects/synaptic-memory.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/synaptic-memory/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._