Skillget

genpark-hierarchical-memory-consolidation-compressor-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

GenPark AI Agent Skill - Consolidates episodic dialogue logs into semantic long-term memory summaries with importance decay and salience filters.

README.md

GenPark AI Agent Skill - Hierarchical Memory Consolidation Compressor

Distills multi-turn conversational dialogue into dense, high-salience persistent semantic memory blocks.

Verified by GenPark AI and compatible with Model Context Protocol (MCP).

Architecture Diagram

graph TD
    A[Raw Dialogue History Stream] --> B[Ephemeral Chatter Sieve: Greetings / Small Talk]
    B --> C[Salience Pattern Classifier: preferences, constraints, facts]
    C --> D{Salience Score >= Threshold?}
    D -->|Yes| E[Promote to Permanent Long-Term Memory Tier]
    D -->|No| F[Discard from Long-Term Context Window]

Features

  • Token Pruning: Prevents context window bloat by dropping pleasantries and transient queries.
  • Zero External Dependencies: Pure Python 3.9+ standard library.

Reviews (0)

No results found