Top 100 Reasoning Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | PageIndex | 33,907 | 2,967 | Python | 66 | 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG | 2026-07-10 |
| 2 | WeKnora | 18,050 | 2,466 | Go | 242 | Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. | 2026-07-09 |
| 3 | clip-as-service | 12,829 | 2,069 | Python | 290 | 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP | 2024-01-23 |
| 4 | HRM | 12,589 | 1,831 | Python | 61 | Hierarchical Reasoning Model Official Release | 2026-03-31 |
| 5 | KAG | 8,883 | 693 | Python | 163 | KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge base... | 2026-01-28 |
| 6 | Awesome-LLM-Strawberry | 6,891 | 370 | - | 8 | A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques. | 2025-12-17 |
| 7 | pyspur | 5,749 | 428 | TypeScript | 29 | A visual playground for agentic workflows: Iterate over your agents 10x faster | 2026-06-29 |
| 8 | deepreasoning | 5,363 | 439 | Rust | 50 | A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models. | 2025-10-07 |
| 9 | node-DeepResearch | 5,198 | 453 | TypeScript | 48 | Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget) | 2026-05-01 |
| 10 | Search-R1 | 5,076 | 452 | Python | 25 | Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL | 2025-11-13 |
| 11 | ARC-AGI | 4,794 | 718 | JavaScript | 28 | The Abstraction and Reasoning Corpus | 2025-04-04 |
| 12 | reasoning-from-scratch | 4,709 | 705 | Jupyter Notebook | 2 | Implement a reasoning LLM in PyTorch from scratch, step by step | 2026-07-06 |
| 13 | tree-of-thoughts | 4,588 | 374 | Python | 12 | Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70% | 2025-07-29 |
| 14 | probability | 4,420 | 1,126 | Jupyter Notebook | 648 | Probabilistic reasoning and statistical analysis in TensorFlow | 2026-07-07 |
| 15 | GLM-4.5 | 4,397 | 466 | Python | 25 | GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | 2026-02-01 |
| 16 | typedb | 4,372 | 368 | Rust | 276 | TypeDB: Built for systems, not records | 2026-07-08 |
| 17 | g1 | 4,178 | 360 | Python | 0 | g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains | 2025-12-30 |
| 18 | ReAct | 4,036 | 386 | Jupyter Notebook | 4 | [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models | 2024-02-06 |
| 19 | mm-cot | 3,985 | 331 | Python | 44 | Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated) | 2024-06-12 |
| 20 | simpleRL-reason | 3,869 | 286 | Python | 33 | Simple RL training for reasoning | 2025-12-23 |
| 21 | PhiCookBook | 3,765 | 506 | Jupyter Notebook | 0 | This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language ... | 2026-07-02 |
| 22 | ReAgent | 3,707 | 527 | Python | 34 | A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.) | 2026-07-02 |
| 23 | Awesome-LLM-Reasoning | 3,646 | 212 | - | 5 | From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓 | 2026-04-20 |
| 24 | DeepSeek-Math | 3,355 | 587 | Python | 39 | DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | 2024-04-15 |
| 25 | terminusdb | 3,345 | 141 | Prolog | 6 | TerminusDB is a distributed, collaborative database designed for building, sharing, versioning, and reasoning on structured data. | 2026-07-09 |
| 26 | pgmpy | 3,294 | 1,130 | Python | 448 | Python Toolkit for Causal and Probabilistic Reasoning | 2026-07-09 |
| 27 | Rapid-MLX | 3,241 | 381 | Python | 29 | The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replace... | 2026-07-10 |
| 28 | Skywork-R1V | 3,160 | 281 | Python | 38 | Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning. | 2025-12-15 |
| 29 | MiniMax-M1 | 3,159 | 284 | Python | 29 | MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. | 2025-07-07 |
| 30 | chain-of-thought-hub | 2,777 | 144 | Jupyter Notebook | 18 | Benchmarking large language models' complex reasoning ability with chain-of-thought prompting | 2024-08-04 |
| 31 | AI-Agents-Projects-Tutorials | 2,775 | 611 | Jupyter Notebook | 5 | Multi-agent systems, memory, planning, reasoning loops | 2026-07-09 |
| 32 | RAGEN | 2,742 | 227 | Python | 28 | RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments. | 2026-04-14 |
| 33 | LISA | 2,656 | 207 | Python | 115 | Project Page for "LISA: Reasoning Segmentation via Large Language Model" | 2025-02-16 |
| 34 | griptape | 2,556 | 248 | Python | 62 | Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. | 2026-07-06 |
| 35 | Cradle | 2,551 | 265 | Python | 19 | The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, ... | 2024-11-07 |
| 36 | Awesome-LLM-Post-training | 2,468 | 164 | Python | 7 | Awesome Reasoning LLM Tutorial/Survey/Guide | 2026-04-06 |
| 37 | Awesome-RL-for-LRMs | 2,467 | 131 | TeX | 3 | A Survey of Reinforcement Learning for Large Reasoning Models | 2025-11-09 |
| 38 | GLM-V | 2,349 | 173 | Python | 11 | GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | 2026-05-16 |
| 39 | llm-reasoners | 2,339 | 203 | Python | 31 | A library for advanced large language model reasoning | 2025-06-10 |
| 40 | open-thoughts | 2,301 | 192 | Python | 6 | Fully open data curation for reasoning models | 2025-12-02 |
| 41 | MiMo | 2,276 | 100 | Python | 56 | MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining | 2025-06-05 |
| 42 | graph-rag-agent | 2,268 | 318 | Python | 32 | 拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction... | 2025-11-05 |
| 43 | Step1X-Edit | 2,234 | 101 | Python | 31 | A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash. | 2026-04-29 |
| 44 | LLaVA-CoT | 2,134 | 82 | Python | 0 | [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning | 2025-12-12 |
| 45 | mcp-shrimp-task-manager | 2,130 | 253 | JavaScript | 34 | Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking... | 2025-08-21 |
| 46 | Embodied_AI_Paper_List | 2,112 | 146 | - | 1 | [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI | 2026-06-10 |
| 47 | Chain-of-ThoughtsPapers | 2,106 | 142 | - | 0 | A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models". | 2023-10-05 |
| 48 | auto-cot | 2,037 | 189 | Jupyter Notebook | 7 | Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated) | 2024-03-13 |
| 49 | Pentest-Swarm-AI | 2,034 | 401 | Go | 11 | Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring... | 2026-06-20 |
| 50 | awesome-explainable-graph-reasoning | 1,989 | 137 | - | 0 | A collection of research papers and software related to explainability in graph machine learning. | 2022-04-04 |
| 51 | continuous-thought-machines | 1,983 | 301 | Python | 3 | Continuous Thought Machines, because thought takes time and reasoning is a process. | 2025-12-29 |
| 52 | PRIME | 1,863 | 116 | Python | 8 | Scalable RL solution for advanced reasoning of language models | 2025-03-18 |
| 53 | openr | 1,848 | 132 | Python | 39 | OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models | 2025-01-17 |
| 54 | knowledge-graphs | 1,794 | 301 | JavaScript | 0 | A collection of research on knowledge graphs | 2022-10-07 |
| 55 | SimpleVLA-RL | 1,766 | 117 | Python | 48 | [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning | 2026-01-06 |
| 56 | WFGY | 1,764 | 163 | Jupyter Notebook | 10 | WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Ea... | 2026-07-09 |
| 57 | viper | 1,716 | 130 | Jupyter Notebook | 15 | Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning" | 2024-01-29 |
| 58 | HRM-Text | 1,645 | 158 | Python | 15 | HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning. | 2026-06-17 |
| 59 | Vision-R1 | 1,583 | 27 | Python | 3 | [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incenti... | 2026-03-20 |
| 60 | Seed1.5-VL | 1,581 | 65 | Jupyter Notebook | 24 | Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks. | 2025-06-14 |
| 61 | ai-agent-papers | 1,547 | 119 | - | 0 | A collection of AI Agents papers (Updated biweekly) | 2026-06-30 |
| 62 | antigravity-cli | 1,538 | 117 | - | 455 | Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal. | 2026-07-08 |
| 63 | Marco-o1 | 1,536 | 81 | Python | 10 | An Open Large Reasoning Model for Real-World Solutions | 2026-06-17 |
| 64 | Awesome_Think_With_Images | 1,487 | 47 | - | 4 | Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation. | 2026-03-09 |
| 65 | octotools | 1,473 | 189 | Python | 3 | OctoTools: An agentic framework with extensible tools for complex reasoning | 2026-05-02 |
| 66 | VibeThinker | 1,465 | 109 | Python | 13 | Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B | 2026-06-17 |
| 67 | reasoning-gym | 1,461 | 122 | Python | 4 | [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards | 2026-04-17 |
| 68 | WebThinker | 1,456 | 141 | Python | 9 | [NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability | 2025-12-08 |
| 69 | Awesome-RL-based-Reasoning-MLLMs | 1,432 | 63 | - | 7 | This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs! | 2026-05-11 |
| 70 | protege | 1,407 | 292 | Java | 411 | Protege Desktop | 2026-04-05 |
| 71 | semantica | 1,399 | 200 | Python | 4 | Semantica • Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI. | 2026-07-09 |
| 72 | AgentCPM-GUI | 1,391 | 131 | Python | 2 | AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution. | 2026-01-11 |
| 73 | KnowLM | 1,385 | 133 | Python | 0 | An Open-sourced Knowledgable Large Language Model Framework. | 2025-01-11 |
| 74 | math | 1,373 | 115 | Python | 16 | The MATH Dataset (NeurIPS 2021) | 2025-09-06 |
| 75 | ThinkSound | 1,369 | 82 | Python | 39 | [NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning. | 2026-04-03 |
| 76 | haft | 1,363 | 102 | Go | 4 | Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more. | 2026-07-06 |
| 77 | MiMo-V2-Flash | 1,354 | 64 | - | 20 | MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model | 2026-01-08 |
| 78 | Awesome-System2-Reasoning-LLM | 1,353 | 80 | Python | 7 | Latest Advances on System-2 Reasoning | 2025-06-08 |
| 79 | pywinassistant | 1,343 | 192 | Python | 10 | The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visuali... | 2025-02-13 |
| 80 | HuatuoGPT-o1 | 1,339 | 133 | Python | 26 | Medical o1, Towards medical complex reasoning with LLMs | 2025-01-20 |
| 81 | Awesome-Agentic-Reasoning | 1,309 | 102 | - | 8 | A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models" | 2026-03-09 |
| 82 | LaTeX_OCR_PRO | 1,305 | 241 | Jupyter Notebook | 13 | 🎨 数学公式识别增强版：中英文手写印刷公式、支持初级符号推导（数据结构基于 LaTeX 抽象语法树）Math Formula OCR Pro, supports handwrite, Chinese-mixed formulas and simple symbol reasoning (based on LaTeX AST). | 2024-06-11 |
| 83 | SoftRas | 1,294 | 159 | Python | 55 | Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning" | 2025-11-24 |
| 84 | understand-r1-zero | 1,268 | 60 | Python | 9 | Understanding R1-Zero-Like Training: A Critical Perspective | 2025-08-27 |
| 85 | Mulberry | 1,244 | 113 | Python | 3 | [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS | 2026-01-16 |
| 86 | Search-o1 | 1,235 | 106 | Python | 2 | 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025] | 2025-11-17 |
| 87 | youtu-graphrag | 1,217 | 182 | Python | 49 | [ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning | 2026-02-26 |
| 88 | R-KV | 1,204 | 194 | Python | 5 | [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models | 2026-07-09 |
| 89 | Kimi-VL | 1,204 | 86 | - | 40 | Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities | 2025-07-15 |
| 90 | MedRAX | 1,193 | 203 | Python | 3 | MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025 | 2025-10-31 |
| 91 | OpenTSLM | 1,183 | 113 | Python | 4 | OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data | 2026-05-05 |
| 92 | chameleon-llm | 1,141 | 82 | Jupyter Notebook | 8 | Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models". | 2023-12-23 |
| 93 | ToRA | 1,118 | 79 | Python | 6 | ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24]. | 2024-02-22 |
| 94 | DeepAgent | 1,112 | 139 | Python | 8 | [WWW‘26 Oral🔥] DeepAgent: A General Reasoning Agent with Scalable Toolsets | 2026-04-13 |
| 95 | SoundMind | 1,109 | 131 | Python | 0 | We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundM... | 2025-11-26 |
| 96 | sgr-agent-core | 1,100 | 173 | Python | 21 | Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community | 2026-05-07 |
| 97 | TTRL | 1,095 | 82 | Python | 17 | [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning | 2026-04-15 |
| 98 | LuaN1aoAgent | 1,090 | 168 | Python | 6 | LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent, using dual-graph reasoning. | 2026-04-13 |
| 99 | LIMO | 1,078 | 54 | Python | 7 | [COLM 2025] LIMO: Less is More for Reasoning | 2025-07-30 |
| 100 | Awesome-AI-Memory | 1,066 | 97 | Python | 1 | Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集中式... | 2026-07-08 |