# spcl/graph-of-thoughts

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Repository: https://github.com/spcl/graph-of-thoughts
Canonical: https://ross.abutalabs.com/products/graph-of-thoughts
Homepage: https://arxiv.org/pdf/2308.09687.pdf
Language: Python
License: NOASSERTION
License Family: other
Topics: graph-structures, graphs, large-language-models, llm, prompt-engineering, prompting, graph-of-thoughts
Last push: 2026-03-24T17:26:16+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 73, release rhythm 8, longevity 79
- inputs: {"age_days": 1111, "days_push": 162, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2833, forks 217 (observed 2026-08-28T04:07:24.440118+00:00)

## What it is
Official Python implementation of the Graph of Thoughts (GoT) framework from ETH Zurich, which models complex problem-solving as a Graph of Operations executed with an LLM as the reasoning engine. It is flexible and extensible, also supporting prior prompting paradigms like Chain-of-Thought and Tree-of-Thoughts.

## Use cases
- solve elaborate reasoning problems with LLMs using graph-structured prompting
- implement chain-of-thought or tree-of-thoughts prompting pipelines
- model multi-step LLM reasoning as a graph of operations
- sort or decompose complex tasks with LLM feedback loops
- experiment with advanced LLM prompting strategies in Python
- score and refine LLM-generated candidate solutions iteratively

## When to choose
- you want graph-structured, non-linear LLM reasoning beyond simple CoT/ToT
- you need a programmable Graph of Operations with scoring and refinement steps
- you are doing research on prompting paradigms and want the reference implementation

## When to avoid
- you just need simple single-prompt LLM calls without structured reasoning
- you want a production chatbot or agent product rather than a research framework
- you need a framework with no LLM API access or offline models

## Facets
- artifact type: framework
- maturity: active
- function: llm-inference, prompt-engineering, agent-framework, rag
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: graph-of-thoughts, chain-of-thought, tree-of-thoughts, reasoning, llm-framework, research, natural-language-processing

## Member repositories
- spcl/graph-of-thoughts (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.440118+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 2026-08-30T07:38:07.282845+00:00, confidence not recorded.
  - readme: https://github.com/spcl/graph-of-thoughts (fetched 2026-08-28T04:07:24.440118+00:00, sha 2cd1d2d0de00)
  - registry_pypi: https://pypi.org/pypi/graph-of-thoughts/json (fetched 2026-08-29T09:53:15.519924+00:00, sha 2622daabf19f)
- Data as of 2026-08-30T08:39:29.467469+00:00.