Neuroplastic Memory

A biologically-inspired persistent memory system for LLMs, modeled on neuroplasticity, consolidation, and sleep.

Mind extracts concepts from conversations, connects them into a persistent knowledge graph, and runsdream cyclesthat consolidate important memories, discover novel associations, and flag contradictions — the same way NREM and REM sleep shape human memory.

[!NOTE] This is a weekend project, vibe-coded with Claude. It's a working prototype and a playground for ideas at the intersection of neuroscience and LLM memory. This is not production software. Expect rough edges. Contributions welcome.

flowchart TB Input(["Conversation Text"]) --> Consolidation subgraph Consolidation["Consolidation Pipeline"] direction LR Extract["LLM Extraction + Affect Signals"] --> Embed["Sentence Embedding"] --> Dedup["Deduplication + Temporal Decay"] end Consolidation --> Appraisal Goals(["Goals"]) -.-> Appraisal subgraph Appraisal["Appraisal System"] direction LR S["Engagement Questions Personal Stake Arousal"] --> Score["Consolidation Score"] N["Novelty"] --> Score F["Frequency"] --> Score G["Goal Relevance"] --> Score end Appraisal --> KG subgraph KG["Knowledge Graph"] Nodes["Concept Nodes"] <--> Edges["Relationship Edges"] end KG <--> Dream subgraph Dream["Dream Engine"] direction LR NREM["NREM Replay"] --> REM["REM Walks"] --> Wake["Waking Gate"] --> Threat["Threat Simulation"] end Query(["Query"]) --> KG KG --> Results(["Ranked Results"]) style Consolidation fill:#d4f0da,stroke:#44cc66,color:#000 style Appraisal fill:#d4e4ff,stroke:#4488ff,color:#000 style KG fill:#e8e8e8,stroke:#888,color:#000 style Dream fill:#ecd4f4,stroke:#aa55dd,color:#000 style Input fill:#4488ff,stroke:#4488ff,color:#fff style Query fill:#ff8833,stroke:#ff8833,color:#fff style Results fill:#ff8833,stroke:#ff8833,color:#fff style Goals fill:#66aa66,stroke:#66aa66,color:#fff

# Install git clone https://github.com/gammon-bio/claude-brain && cd claude-brain uv sync # Set your Anthropic API key echo "ANTHROPIC_API_KEY=sk-ant-..." > .env

Add the MCP server to your Claude Desktop config (claude_desktop_config.json):

{ "mcpServers": { "neuroplastic-memory": { "command": "/absolute/path/to/mind/.venv/bin/python", "args": ["-m", "mind"], "cwd": "/absolute/path/to/mind", "env": { "PYTHONPATH": "/absolute/path/to/mind/src" } } } }

You: "Store this: [paste conversation or research notes]" Claude: → calls memory_store → extracts concepts, builds graph You: "Run a dream cycle" Claude: → calls memory_dream → NREM consolidation, REM exploration, threat scan You: "What do you remember about X?" Claude: → calls memory_retrieve → ranked results with connection context

The memory graph persists globally at~/.neuroplastic-memory/, so it works across any chat or project. To have Claude use it automatically, go toSettings → Generaland add the following to yourPersonal Preferences:

I use a neuroplastic memory system via MCP tools. For every conversation: 1. At the START, call memory_retrieve with my first message to check for relevant prior context. 2. When I share substantive information — research findings, technical decisions, strategic insights, project updates — call memory_store with the key content. Do not use built-in memory. Use the MCP tool memory_store. 3. I may ask you to run memory_dream or memory_dream_report at any time.

This gives you a single shared memory across all conversations. To keep memory siloed to a specific project instead, add the same instructions to that project'sProject Instructionsrather than your global preferences.

Turns raw text into graph knowledge. An LLM extracts concepts and relationships (with affect signals — how strongly the user emphasized each idea). Each concept is embedded into a dense vector, checked against existing nodes for deduplication, and integrated into the graph. An exponential temporal decay runs on every edge: recently activated connections survive, stale ones are pruned. This is Hebbian plasticity — connections that fire together wire together, and connections that don't are forgotten.

Every new concept is scored across four channels before entering the graph:

These combine into a singleconsolidation score(weighted sum, configurable) that determines a node's survival fitness — how likely it is to be replayed during NREM and to resist decay.

Conflict boost:If a concept lands near existingcontradictsedges, salience receives a +0.3 additive boost that can push the score to 1.0 regardless of other signals. This models an adrenaline-like override — contradictory information triggers immediate alerting, ensuring it isn't lost to decay before the threat simulation phase can flag it.

Offline processing modeled on sleep neuroscience. Four phases run in sequence:

NREM (slow-wave replay):High-salience nodes are replayed and their edge weights are strengthened, mimicking the hippocampal-cortical replay observed in slow-wave sleep. Edges below a pruning threshold are removed.

REM (creative exploration):Biased random walks from seed nodes traverse the graph. At each step, the walker mayjumpto a semantically similar but topologically distant node — creative teleportation. When two nodes on a walk are embedding-similar but share no edge, a provisional connection is proposed.

Waking evaluation:Provisional edges are re-evaluated at a stricter threshold. Only connections that survive this gate are promoted to realdream_connectionedges in the graph. This prevents hallucinated associations from polluting the knowledge base.

Threat simulation:Scans high-confidence nodes for nearbycontradictsedges and flags them. These contradiction alerts surface conflicting information that may need resolution.

Users can declare goals ("understand X", "investigate Y"). Each goal is embedded and persisted. During consolidation, every new concept is scored for relevance against active goals — concepts aligned with what you're trying to learn are prioritized for consolidation and survival. Goals are managed through thememory_goalsMCP tool and stored ingoals.jsonalongside the graph.

A NetworkX-backed directed graph with typed edges (causes,contradicts,part_of,dream_connection,goal_linked,related_to). Each node carries its embedding, appraisal scores, access count, timestamps, and metadata. The graph persists to JSON and supports similarity search via cosine distance over embeddings.

python3 viz/serve.py [port] [graph_path] # Defaults: port 8080, graph ~/.neuroplastic-memory/graph.json

Openhttp://localhost:8080for an interactive 3D force-directed graph.

Edgesare thicker for higher weight. Animated particles appear on edges with weight > 0.5.

Controls:Refresh, Auto-refresh (30s), Play Dream (replays walk paths with jump markers), Speed slider. Hover any node to see its label, origin, and scores.

All parameters are tunable at runtime viamemory_tuneor insrc/mind/schemas/config.py:

Appraisal weights:alpha/beta/gamma/delta(0.25 each) — balance salience, novelty, goal-relevance, and retrieval frequency in the consolidation score.

Salience sub-weights:salience_engagement_weight(0.2),salience_question_weight(0.2),salience_personal_weight(0.3),salience_arousal_weight(0.3) — control which behavioral signals drive salience.

Dream parameters:rem_jump_probability(0.3),rem_walk_steps(10),rem_seed_count(5),waking_threshold(0.35),nrem_salience_threshold(0.3)

Consolidation:decay_constant(0.01),novelty_threshold(0.7)

161 tests covering appraisal scoring, consolidation pipeline, dream phases, graph operations, goal persistence, affect metadata, MCP tools, and integration.

614 million contacts, live SMTP-verified. Invalid emails cost you $0. Connect Argorant with any Agent through CLI, MCP or API and build verified lists in Claude, GPT or Hermes.

Chinese writing toolbox for Claude Code: text analysis, outline generation, GB/T 7714 references,character frequency

Hydrolix time-series datalake integration providing schema exploration and query capabilities to LLM-based workflows.

Cactal is the website platform for AI agents. Connect Claude Code, Cursor, or anything that speaks MCP, and your agent gets the tools to design, build, host, and operate production websites: source code, CMS, assets, domains, analytics, and publishing.

A lightweight MCP server for connecting to Apache Doris and other MySQL-compatible databases, providing tools and prompts for LLM applications.

A local MCP server that gives Claude Code, Cursor and Codex read access to your DynamoDB schema and items, with every write staged for human review.

C# SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.

Enables persistent knowledge storage for Claude using a knowledge graph with multiple database backends like PostgreSQL and SQLite.

Enables persistent memory for Claude using a knowledge graph stored in local JSON files.

Build and access a personal LLM knowledge base from your editor or client without any infrastructure setup.