genpark-hierarchical-task-network-htn-planner-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • 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 Gecti
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

GenPark AI Agent Skill - Hierarchical Task Network (HTN) decomposition engine recursively expanding compound high-level goals into primitive executable action sequences.

README.md

GenPark AI Agent Skill - Hierarchical Task Network (HTN) Planner

A pure Python standard library skill implementing Hierarchical Task Network (HTN) planning (SHOP2 style). Recursively decomposes complex agent goals into executable primitive action DAGs with state precondition and add/delete effect verification.

Architecture

graph TD
    A[Compound High-Level Goal] --> B{Method Decomposition Engine}
    B -->|Preconditions Satisfied| C[Subtasks Network]
    C --> D{Primitive Operator Checker}
    D -->|Primitive| E[Validate Operator Preconditions & Apply Effects]
    D -->|Compound| B
    E --> F[Linear Executable Primitive Action Plan]

Features

  • Deterministic DFS Search: Guarantees sound plan generation.
  • Precondition & Effect Tracking: Maintains ground predicate truth.
  • Zero Pip Dependencies: Standard Library Only.

Citations & Ecosystem

Yorumlar (0)

Sonuc bulunamadi