Skillget

genpark-graph-random-walk-personalized-pagerank-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 - Computes Personalized PageRank (PPR) over agent memory graphs for context-sensitive entity relevance and associative recall.

README.md

GenPark AI Agent Skill - Graph Random Walk Personalized PageRank

A zero-pip-dependency Python standard library skill computing Personalized PageRank (PPR) via power iteration over agent memory networks. Retrieves context-relevant concepts through associative graph activation.

Architecture

graph TD
    A[Seed Query Nodes] --> B[Personalized Teleport Vector v]
    C[Heterogeneous Memory Graph] --> D[Weighted Adjacency Transition Matrix W]
    B --> E[PPR Power Iteration Engine]
    D --> E
    E --> F[Stationary Activation Distribution p*]
    F --> G[Top-K Associative Memory Retrieval]

Features

  • Power Iteration with Dangling Mass Redistribution: Exact mathematical convergence guaranteed.
  • Context-Sensitive Associative Recall: Finds non-adjacent but conceptually tightly-linked entities.
  • Pure Python 3.9+ Standard Library: No networkx or scipy required.

Citations & Ecosystem

Reviews (0)

No results found