# 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%

Repository: https://github.com/kyegomez/tree-of-thoughts
Canonical: https://ross.abutalabs.com/products/tree-of-thoughts
Homepage: https://discord.gg/qUtxnK2NMf
Language: Python
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, chatgpt, gpt4, multimodal, prompt-engineering, deep-learning, prompt, prompt-learning, prompt-tuning
Last push: 2025-07-29T05:16:50+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 34, release rhythm 8, longevity 85
- inputs: {"age_days": 1200, "days_push": 400, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4591, forks 376 (observed 2026-08-28T04:08:54.708749+00:00)

## What it is
A Python library implementing the Tree of Thoughts algorithm for deliberate, multi-step problem solving with large language models. It provides plug-and-play agents (e.g., DFS-based ToT agents) that wrap your own LLM calls to improve model reasoning.

## Use cases
- improve llm reasoning on complex problems
- run tree of thoughts prompting with gpt-4
- solve math and planning tasks with deliberate search
- plug my own model into a tree of thoughts agent
- compare chain of thought vs tree of thoughts reasoning

## When to choose
- you want a ready-made Tree of Thoughts implementation to boost LLM reasoning
- you need a plug-and-play agent that works with your own model or OpenAI API
- you are experimenting with search-based prompting strategies like DFS

## When to avoid
- you need a production-grade, well-maintained reasoning framework with broad support
- you want simple single-shot prompting without extra token cost
- you need non-Python environments

## Facets
- artifact type: library
- maturity: active
- function: prompt-engineering, llm-inference, agent-framework, machine-learning
- domain: artificial-intelligence, large-language-models
- platform: python
- tags: tree-of-thoughts, reasoning, llm, dfs-search, plug-and-play, natural-language-processing

## Member repositories
- kyegomez/tree-of-thoughts (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:54.708749+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:50.701335+00:00, confidence not recorded.
  - readme: https://github.com/kyegomez/tree-of-thoughts (fetched 2026-08-28T04:08:54.708749+00:00, sha 368b3cabe8ff)
  - homepage: https://discord.gg/qUtxnK2NMf (fetched 2026-08-29T09:05:13.165669+00:00, sha 3c791664bd51)
  - registry_pypi: https://pypi.org/pypi/tree-of-thoughts/json (fetched 2026-08-29T09:05:13.175246+00:00, sha 441b94905379)
- Data as of 2026-08-30T08:39:29.467469+00:00.