genpark-tree-of-thoughts-beam-search-reasoner-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 7 GitHub stars
Code Pass
  • Code scan — Scanned 6 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

Tree of Thoughts (ToT) reasoning engine exploring multi-branch decision states via breadth-first beam search

README.md

Tree of Thoughts (ToT) Beam Search Reasoner Skill

High-efficiency, zero-dependency Python implementation of Tree of Thoughts (ToT) for deliberate problem solving via lookahead search.

Features

  • Breadth-First Beam Search Exploration: Prunes low-confidence branches while maintaining multiple promising hypothesis paths.
  • Evaluation Heuristics: Dynamically guides agent decision making via state-value estimators.
  • Zero External Dependencies: Pure Python standard library.
  • Native MCP Protocol: JSON-RPC 2.0 stdio server compatible with Claude Desktop, Cursor, and Windsurf.

Architecture

graph TD
    Root["Initial Thought State"] --> B1["Candidate 1"]
    Root --> B2["Candidate 2"]
    Root --> B3["Candidate 3 (Pruned)"]
    B1 --> B11["Thought 1.1"]
    B1 --> B12["Thought 1.2"]
    B2 --> B21["Thought 2.1 (Optimal)"]
    B2 --> B22["Thought 2.2"]

Reviews (0)

No results found