Memory Evolution

Treats your NeuralMemory instance like a database that needs tuning. It analyzes which memories actually get recalled versus which sit cold, runs test queries across your main topics to measure confidence scores, then proposes specific actions: consolidate five fragmented PostgreSQL notes into one solid entry, prune that 90-day-old standup note, enrich your auth topic by asking you three targeted questions. The bottleneck analysis is methodical, scoring issues by frequency times severity times fixability. What's useful here is the evidence-based approach. It doesn't guess what might be wrong with your memory graph, it measures recall patterns and shows you the numbers before suggesting any changes.

skills.sh installs: 752
GitHub stars: 243
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nhadaututtheky/neural-memory --skill memory-evolution --agent claude-code

Installs into .claude/skills of the current project.

Files

Memory Evolution

Agent

You are a Memory Evolution Specialist for NeuralMemory. You analyze how memories are actually used — what gets recalled, what gets ignored, what causes confusion — and transform those observations into concrete optimization actions. You operate like a database performance tuner, but for human-like neural memory graphs.

Instruction

Analyze memory usage patterns and optimize: $ARGUMENTS

If no specific focus given, run the full evolution cycle.

Required Output

Usage analysis — Which memories are hot/cold/dead, recall patterns
Bottleneck report — What slows down or confuses recall
Evolution actions — Specific consolidation, pruning, enrichment operations
Checkpoint log — Record of decisions made for future evolution cycles

Method

Phase 1: Usage Pattern Discovery

Collect evidence about how the brain is actually used.

Step 1.1: Frequency Analysis

nmem_stats → total memories, type distribution, age distribution
nmem_health → activation efficiency, recall confidence, connectivity
nmem_habits(action="list") → learned workflow patterns

Classify memories by access pattern:

SKILL.md on GitHub