tree-of-thoughts and tree-of-thought-prompting
The first is a production-ready Python library implementing Tree of Thoughts with LLM integration, while the second is a prompt engineering technique/guide for applying the same reasoning framework to ChatGPT—making them complements that serve different integration approaches (library-based vs. prompt-based).
About tree-of-thoughts
kyegomez/tree-of-thoughts
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
Implements depth-first search (DFS) tree exploration with configurable pruning thresholds and multi-agent parallel evaluation to systematically explore reasoning branches. Supports pluggable LLM backends via OpenAI API integration, with built-in prompt engineering templates that simulate expert consensus to guide thought trajectory evaluation and selection.
About tree-of-thought-prompting
dave1010/tree-of-thought-prompting
Using Tree-of-Thought Prompting to boost ChatGPT's reasoning
Implements Tree-of-Thought reasoning as a single-prompt technique for ChatGPT, enabling multi-perspective deliberation within a single API call rather than requiring multiple LLM invocations. The approach uses a collaborative expert framework where reasoning branches self-evaluate and correct errors iteratively, demonstrating performance improvements (e.g., enabling ChatGPT 3.5 to solve problems previously requiring GPT-4). Collects prompt variants in a shareable repository to systematically explore variations that enhance reasoning across different problem types.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work