Reasoning Chain Frameworks Prompt Engineering Tools

Tools and implementations of structured reasoning methods (Chain-of-Thought, Tree-of-Thoughts, Graph-of-Thoughts, etc.) that enhance LLM problem-solving through multi-step or graph-based exploration. Does NOT include general prompt management, optimization, or application-specific prompt libraries without novel reasoning architectures.

There are 34 reasoning chain frameworks tools tracked. 3 score above 50 (established tier). The highest-rated is kyegomez/tree-of-thoughts at 62/100 with 4,571 stars and 175 monthly downloads.

Get all 34 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=prompt-engineering&subcategory=reasoning-chain-frameworks&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	kyegomez/tree-of-thoughts Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem...	62	Established	4,571	Python
2	spcl/graph-of-thoughts Official Implementation of "Graph of Thoughts: Solving Elaborate Problems...	54	Established	2,614	Python
3	kyegomez/the-compiler Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!	52	Established	145	Python
4	habedi/cogitator A Python toolkit for chain-of-thought prompting 🐍	46	Emerging	184	Python
5	amazon-science/auto-cot Official implementation for "Automatic Chain of Thought Prompting in Large...	46	Emerging	2,012	Jupyter Notebook
6	atfortes/Awesome-LLM-Reasoning From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓	46	Emerging	3,558	—
7	zjunlp/Prompt4ReasoningPapers [ACL 2023] Reasoning with Language Model Prompting: A Survey	44	Emerging	999	—
8	dave1010/tree-of-thought-prompting Using Tree-of-Thought Prompting to boost ChatGPT's reasoning	44	Emerging	815	—
9	jeffhj/LM-reasoning This repository contains a collection of papers and resources on Reasoning...	40	Emerging	568	—
10	kyegomez/Algorithm-Of-Thoughts My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas...	40	Emerging	100	Python
11	logikon-ai/awesome-deliberative-prompting Awesome deliberative prompting: How to ask LLMs to produce reliable...	36	Emerging	123	—
12	Oznake/Awesome-LLM-reasoning-papers This repository offers a well-organized collection of resources focused on...	35	Emerging	5	—
13	holarissun/PanelGPT We introduce new zero-shot prompting magic words that improves the reasoning...	30	Emerging	171	Python
14	RoT-llm/Reversal-of-Thought [ACL 2025] Demo code for the paper "Reversal of Thought: Enhancing Large...	28	Experimental	6	Python
15	edoardoavenia/chain-of-thought-master AI assistant specialized in Chain of Thought (CoT), logical reasoning and...	24	Experimental	2	—
16	Alab-NII/chain-of-thought Research papers about Chain of Thought (CoT)	24	Experimental	59	—
17	amirkiarafiei/chain-of-thought-visualizer A Visualizer for Chain-of-Thought Prompting of LLMs	21	Experimental	2	TypeScript
18	Chihaya-Yuka/Multiplex-CoT [arXiv 2501.13117]The Multiplex CoT makes AI more thoughtful.	20	Experimental	19	Jupyter Notebook
19	TEJA4704/prompt-engineering-toolkit Advanced prompt engineering techniques: Chain-of-Thought, Tree-of-Thoughts,...	20	Experimental	1	Python
20	zjunlp/knowledge-rumination [EMNLP 2023] Knowledge Rumination for Pre-trained Language Models	20	Experimental	17	Python
21	kyegomez/LOGICGUIDE Plug in and Play implementation of "Certified Reasoning with Language...	20	Experimental	16	Python
22	hoadm-net/MathCoRL Comprehensive framework for mathematical reasoning research with dual...	19	Experimental	—	Python
23	HIDEKI-SQ/cot-backfire When does chain-of-thought prompting backfire? Experiments identifying the...	19	Experimental	—	Jupyter Notebook
24	machinemindsai/secrets-of-tree-of-thoughts-tot Secrets of Tree of Thoughts for Programmers (Preview)	16	Experimental	17	—
25	remember00000/Awesome-DeepSeek-R1-Resources Explore DeepSeek R1🚀: reproduction guides, papers, insightful tweets&blogs...	16	Experimental	4	—
26	msmrexe/llm-math-reasoning-analysis An evaluation of prompting techniques (Zero-Shot CoT, Few-Shot,...	16	Experimental	1	Python
27	DHIWAHAR-K/Beyond-English-Multilingual-Self-Consistency-for-Robust-LLM-Reasoning Research: Does multilingual self-consistency improve LLM reasoning beyond...	14	Experimental	—	Jupyter Notebook
28	IngredientPreppers/Awesome-LLM-reasoning-papers Paper reading list for LLM/MLLM reasoning	14	Experimental	4	—
29	wolfenix/llm-math-reasoning-analysis 🔍 Analyze the mathematical reasoning abilities of the Mistral-7B model using...	14	Experimental	—	HTML
30	hathienloc131/auto-graph-of-thoughts 💭Auto Graph of Thoughts: A Hands-free and Cost Effective Method for using...	14	Experimental	9	Python
31	andreanstev/AutoDiCoT_prompt Automatic Directed CoT (AutoDiCoT) implementation.	13	Experimental	2	Jupyter Notebook
32	abisliouk/HS-MATH-LLM Evaluate high school math reasoning in LLMs with baseline and...	12	Experimental	1	Python
33	SuperBruceJia/GSM8K-Consistency GSM8K-Consistency is a benchmark database for analyzing the consistency of...	11	Experimental	2	—
34	holistech/cot_chat A simple Chain of Thought streamlit chat application to explore the power of...	11	Experimental	—	Python

Comparisons in this category

tree-of-thoughts and tree-of-thought-prompting (62 vs 44) tree-of-thoughts and the-compiler (62 vs 52) tree-of-thoughts and Algorithm-Of-Thoughts (62 vs 40) Awesome-LLM-Reasoning and Awesome-LLM-reasoning-papers (46 vs 35) graph-of-thoughts and Algorithm-Of-Thoughts (54 vs 40) Awesome-LLM-reasoning-papers and LM-reasoning (35 vs 40)