jmeyer1980 avatar

Neurodivergent Memory

jmeyer1980/neurodivergent-memory

A persistent knowledge graph that organizes memories into five cognitive districts (logical analysis, emotional processing, practical execution, vigilant monitoring, creative synthesis) and connects them bidirectionally. Uses BM25 semantic search with no cloud LLM dependency. Exposes tools for storing, retrieving, updating, and traversing memories, plus graph operations like connect_memories and related_to that blend proximity with semantic ranking. Includes prompts for guided exploration and synthesis that mirror as tools for clients with limited prompt support. Memory nodes carry emotional valence, intensity, epistemic status, and project attribution. Built around FractalSemantics addressing where every entity traces ancestry to a single LUCA anchor point. Persists to local JSON snapshots with WAL support and offers bulk import with dedupe policies.

GitHub stars
12
tools
16
transport
STDIO
last updated
Mar 29, 2026

Tools

16 tools

Public tool metadata for what this MCP can expose to an agent.

store_memoryCreate new memory nodes with optional emotional valence and intensity

Create new memory nodes with optional emotional valence and intensity

No parameter schema in public metadata yet.

retrieve_memoryFetch a specific memory by ID

Fetch a specific memory by ID

No parameter schema in public metadata yet.

update_memoryModify content, tags, district, emotional_valence, intensity, or project attribution

Modify content, tags, district, emotional_valence, intensity, or project attribution

No parameter schema in public metadata yet.

delete_memoryRemove a memory and all its connections

Remove a memory and all its connections

No parameter schema in public metadata yet.

connect_memoriesCreate bidirectional edges between memory nodes

Create bidirectional edges between memory nodes

No parameter schema in public metadata yet.

search_memoriesBM25-ranked semantic search with optional goal context, recency bias, and filters (district, project_id, tags, epistemic status, emotional valence, intensity, min_score)

BM25-ranked semantic search with optional goal context, recency bias, and filters (district, project_id, tags, epistemic status, emotional valence, intensity, min_score)

No parameter schema in public metadata yet.

traverse_fromGraph traversal up to N hops from a starting memory

Graph traversal up to N hops from a starting memory

No parameter schema in public metadata yet.

related_toFind memories by graph proximity + BM25 semantic blend, with optional goal context and epistemic-status filters

Find memories by graph proximity + BM25 semantic blend, with optional goal context and epistemic-status filters

No parameter schema in public metadata yet.

list_memoriesPaginated listing with optional district/archetype/project_id/epistemic-status filters

Paginated listing with optional district/archetype/project_id/epistemic-status filters

No parameter schema in public metadata yet.

memory_statsAggregate statistics (totals, per-district/per-project counts, most-accessed, orphans) with optional project scope

Aggregate statistics (totals, per-district/per-project counts, most-accessed, orphans) with optional project scope

No parameter schema in public metadata yet.

server_handshakeReturn runtime server identity/version details for explicit client-side version confirmation

Return runtime server identity/version details for explicit client-side version confirmation

No parameter schema in public metadata yet.

storage_diagnosticsShow the resolved snapshot path, WAL path, and effective persistence source in one response

Show the resolved snapshot path, WAL path, and effective persistence source in one response

No parameter schema in public metadata yet.

import_memoriesBulk-import from inline JSON entries or a snapshot file_path, with dry_run, dedupe policies, and explicit snapshot migration flags

Bulk-import from inline JSON entries or a snapshot file_path, with dry_run, dedupe policies, and explicit snapshot migration flags

No parameter schema in public metadata yet.

prepare_memory_city_contextTool mirror of explore_memory_city for clients that support tools but do not invoke MCP prompts

Tool mirror of explore_memory_city for clients that support tools but do not invoke MCP prompts

No parameter schema in public metadata yet.

prepare_synthesis_contextTool mirror of synthesize_memories for prompt-limited clients

Tool mirror of synthesize_memories for prompt-limited clients

No parameter schema in public metadata yet.

prepare_packetized_synthesis_contextTool mirror of synthesize_memory_packets for prompt-limited or attachment-constrained clients

Tool mirror of synthesize_memory_packets for prompt-limited or attachment-constrained clients

No parameter schema in public metadata yet.

Sponsors

Readme

neurodivergent-memory MCP Server

npm version Docker Image Version License: MIT Node 24 LTS


View the full README on GitHub

Details

Repository
github.com/jmeyer1980/neurodivergent-memory
Categories
AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
Package
neurodivergent-memory
Transport
STDIO
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1verivus-oss avatarLLM CLI Gatewayverivus-oss/llm-cli-gatewayOne MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.8stars
2kapillamba4 avatarMeta Prompt Mcpkapillamba4/meta-prompt-mcpMCP server providing official Google and Anthropic prompting guides for meta-prompt generation.2stars
3capybearista avatarGemini Researchercapybearista/gemini-researcherStateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage0stars
4tekgnosis avatarGnosis Memorytekgnosis/gnosismemoryPersistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.0stars
5flsteven87 avatarLlm Wiki Mcpflsteven87/llm-wiki-mcpMCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.0stars
6agenson-tools avatarAgent Output Guardagenson-tools/agent-output-guard-mcpValidate and verify data from other agents before acting on it. Zero LLM costs.0stars