#Chain-of-thought

Showing 51 of 51 repositories tagged #chain-of-thought, ranked by stars

RUCAIBox
RUCAIBox
LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

Score
0
โ˜… 12.2k โ‘‚ 935 โ€”
Python
NirDiamant
NirDiamant
Prompt_Engineering

22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

Score
100
โ˜… 7.7k โ‘‚ 985 +5/day
Jupyter Notebook
hijkzzz
hijkzzz
Awesome-LLM-Strawberry

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 ๐Ÿ“ and reasoning techniques.

Score
95
โ˜… 6.9k โ‘‚ 370 โ€”
winfunc
winfunc
deepreasoning

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.

Score
0
โ˜… 5.4k โ‘‚ 439 โ€”
Rust
Kiln-AI
Kiln-AI
Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Score
33
โ˜… 5.0k โ‘‚ 377 +2/day
Python
FellouAI
FellouAI
eko

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

Score
97
โ˜… 4.9k โ‘‚ 440 +1/day
TypeScript
rasbt
rasbt
reasoning-from-scratch

Implement a reasoning LLM in PyTorch from scratch, step by step

Score
67
โ˜… 4.7k โ‘‚ 705 +22/day
Jupyter Notebook
algorithmicsuperintelligence
algorithmicsuperintelligence
optillm

Optimizing inference proxy for LLMs

Score
100
โ˜… 4.2k โ‘‚ 368 +6/day
Python
atfortes
atfortes
Awesome-LLM-Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 ๐Ÿ“

Score
89
โ˜… 3.6k โ‘‚ 212 +3/day
DSXiangLi
DSXiangLi
DecryptPrompt

ๆ€ป็ป“Prompt&LLM่ฎบๆ–‡๏ผŒๅผ€ๆบๆ•ฐๆฎ&ๆจกๅž‹๏ผŒAIGCๅบ”็”จ

Score
92
โ˜… 3.4k โ‘‚ 322 โ€”
EgoAlpha
EgoAlpha
prompt-in-context-learning

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

Score
87
โ˜… 2.2k โ‘‚ 189 โ€”
Jupyter Notebook
amazon-science
amazon-science
auto-cot

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

Score
79
โ˜… 2.0k โ‘‚ 189 โ€”
Jupyter Notebook
OpenDriveLab
OpenDriveLab
DriveLM

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

Score
63
โ˜… 1.3k โ‘‚ 89 +1/day
HTML
zjunlp
zjunlp
Prompt4ReasoningPapers

[ACL 2023] Reasoning with Language Model Prompting: A Survey

Score
61
โ˜… 1.0k โ‘‚ 68 โ€”
UditAkhourii
UditAkhourii
adhd

ADHD โ€” a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.

Score
0
โ˜… 925 โ‘‚ 50 +11/day
TypeScript
jxzhangjhu
jxzhangjhu
Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

Score
84
โ˜… 826 โ‘‚ 59 โ€”
jeffhj
jeffhj
LM-reasoning

This repository contains a collection of papers and resources on Reasoning in Large Language Models.

Score
53
โ˜… 572 โ‘‚ 37 โ€”
agencyenterprise
agencyenterprise
PromptInject

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. ๐Ÿ† Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Score
82
โ˜… 503 โ‘‚ 53 +1/day
Python
zchuz
zchuz
CoT-Reasoning-Survey

[ACL 2024] A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

Score
50
โ˜… 500 โ‘‚ 16 โ€”
IAAR-Shanghai
IAAR-Shanghai
Awesome-Attention-Heads

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Score
45
โ˜… 412 โ‘‚ 12 +2/day
TeX
zjunlp
zjunlp
EasyInstruct

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

Score
47
โ˜… 407 โ‘‚ 36 โ€”
Python
yeahhe365
yeahhe365
Prisma

ๅŸบไบŽ Gemini ็š„ๅฏ่ง†ๅŒ–ๅคšๆ™บ่ƒฝไฝ“ๆทฑๅบฆๆŽจ็†ๅผ•ๆ“Ž | A visual multi-agent deep reasoning engine powered by Gemini, featuring dynamic planning, chain-of-thought visualization, and multi-session management. Built with React 19 + TypeScript + Vite 6.

Score
100
โ˜… 336 โ‘‚ 32 +1/day
TypeScript
li2109
li2109
langtorch

๐Ÿ”ฅ Building composable LLM applications & workflow with Java.

Score
42
โ˜… 305 โ‘‚ 44 โ€”
Java
raunak-agarwal
raunak-agarwal
instruction-datasets

Datasets for Instruction Tuning of Large Language Models

Score
37
โ˜… 261 โ‘‚ 13 โ€”
ckelsoe
ckelsoe
prompt-architect

Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE, TIDD-EC, RTF, CoT, CoD)

Score
0
โ˜… 235 โ‘‚ 28 +4/day
Python
Fr0zenCrane
Fr0zenCrane
UniCoT

[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

Score
100
โ˜… 232 โ‘‚ 7 +1/day
Python
WHU-ZQH
WHU-ZQH
ChatGPT-vs.-BERT

๐ŸŽ[ChatGPT4NLU] A Comparative Study on ChatGPT and Fine-tuned BERT

Score
32
โ˜… 191 โ‘‚ 7 โ€”
Python
habedi
habedi
cogitator

A Python toolkit for chain-of-thought prompting ๐Ÿ

Score
74
โ˜… 187 โ‘‚ 6 โ€”
Python
paradroidlabs
paradroidlabs
scratchpad

This framework works as a form of user/machine calibration, with a focus on user-context and user-intent, deconstructing your ideas logically from A to B to Z.

Score
76
โ˜… 187 โ‘‚ 31 โ€”
LJungang
LJungang
Awesome-Video-Reasoning-Landscape

๐Ÿ”ฅAn open-source survey of the latest video reasoning tasks, paradigms, and benchmarks.

Score
0
โ˜… 186 โ‘‚ 8 โ€”
holarissun
holarissun
PanelGPT

We introduce new zero-shot prompting magic words that improves the reasoning ability of language models: panel discussion!

Score
29
โ˜… 174 โ‘‚ 12 โ€”
Python
IAAR-Shanghai
IAAR-Shanghai
ICSFSurvey

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation๐Ÿ“ and hallucination alleviation๐Ÿ„.

Score
26
โ˜… 173 โ‘‚ 5 โ€”
Jupyter Notebook
Denis2054
Denis2054
Building-Business-Ready-Generative-AI-Systems

This GitHub repository contains the complete code for building Business-Ready Generative AI Systems (GenAISys) from scratch. It guides you through architecting and implementing advanced AI controllers, intelligent agents, and dynamic RAG frameworks. The projects demonstrate practical applications across various domains.

Score
71
โ˜… 164 โ‘‚ 50 โ€”
Jupyter Notebook
heavenaruba
heavenaruba
codified-prompt-rule-engine

Top 10 Claude Prompt Optimization Frameworks 2026

Score
66
โ˜… 153 โ‘‚ 0 โ€”
HTML
AgustiPuigserver
AgustiPuigserver
opus-prompt-architect

Best Prompt Engineering Tools for 2026 AI Workflow Optimization

Score
66
โ˜… 153 โ‘‚ 0 โ€”
HTML
kyegomez
kyegomez
the-compiler

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

Score
24
โ˜… 145 โ‘‚ 17 โ€”
Python
logikon-ai
logikon-ai
awesome-deliberative-prompting

Awesome deliberative prompting: How to ask LLMs to produce reliable reasoning and make reason-responsive decisions.

Score
21
โ˜… 125 โ‘‚ 8 โ€”
OttoRenner
OttoRenner
Gentle-Coding

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

Score
58
โ˜… 105 โ‘‚ 7 โ€”
HTML
declare-lab
declare-lab
Emma-X

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Score
18
โ˜… 84 โ‘‚ 8 โ€”
Python
The-Martyr
The-Martyr
Awesome-Multimodal-Reasoning

Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs

Score
55
โ˜… 77 โ‘‚ 6 โ€”
chainstacklabs
chainstacklabs
web3-ai-trading-agent

Build an Autonomous Web3 AI Trading Agent (BASE + Uniswap V4 example)

Score
0
โ˜… 66 โ‘‚ 18 โ€”
Python
Alab-NII
Alab-NII
chain-of-thought

Research papers about Chain of Thought (CoT)

Score
13
โ˜… 64 โ‘‚ 5 +1/day
om-ai-lab
om-ai-lab
open-agent-leaderboard

Reproducible Language Agent Research

Score
11
โ˜… 36 โ‘‚ 2 โ€”
Python
Peuqui
Peuqui
AIfred-Intelligence

๐Ÿคต AIfred-Intelligence โ€” self-hosted Multi-Agent Assistant with Debate Modes (Symposion/Tribunal), Voice (STT + Streaming-TTS), RAG with Long-Term Memory, Web Research and Tool-Calling. Reachable via Web-UI or Telegram/Discord/Email/EPIM. Multi-Backend: llama-swap, Ollama, vLLM, TabbyAPI.

Score
39
โ˜… 33 โ‘‚ 3 โ€”
Python
jxhuang0508
jxhuang0508
Awesome-LLM-Reasoning-OpenAI-o1

Awesome LLM papers, news and projects about learning to reason with LLM, OpenAI o1, reasonning techniques, chain-of-thought (COT), Large Language Model, Straberry

Score
5
โ˜… 28 โ‘‚ 3 โ€”
tsinghua-fib-lab
tsinghua-fib-lab
SmartAgent

The official repository of "SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World".

Score
8
โ˜… 27 โ‘‚ 1 โ€”
atfortes
atfortes
LLMSymbolicReasoningBench

Synthetic data generation for evaluating LLM symbolic and logic reasoning

Score
0
โ˜… 23 โ‘‚ 1 โ€”
Python
sarkar-dipankar
sarkar-dipankar
fragaria

Fragaria is a powerful and flexible Chain of Thought (CoT) reasoning API that leverages various Language Model (LLM) providers and incorporates Reinforcement Learning (RL) techniques to solve complex problems and answer intricate questions.

Score
3
โ˜… 21 โ‘‚ 1 โ€”
Python
CheswickDEV
CheswickDEV
claude-opus-4.6-prompt-optimizer

A meta-prompting system that transforms raw prompts into production-ready, XML-structured prompts optimized for Claude Opus 4.6. 10 codified rules, 10-component framework, complexity-based routing โ€” based on Anthropic's official best practices.

Score
34
โ˜… 19 โ‘‚ 4 โ€”
eon01
eon01
LLMPromptEngineeringForDevelopersFiles

This repository contains the code snippets used in "LLM Prompt Engineering For Developers"

Score
0
โ˜… 14 โ‘‚ 5 โ€”
faveos8758
faveos8758
reflexion-agent-ts

Self-improving LLM agent in TypeScript using Reflexion (verbal RL): custom evaluators, reflexion memory, HTTP API, CLI. Built with Vercel AI SDK.

Score
16
โ˜… 11 โ‘‚ 0 โ€”
TypeScript
Related Topics
#llm#prompt-engineering#large-language-models#chatgpt#reasoning#in-context-learning#ai#python#gpt-3#llms#openai#reinforcement-learning

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly