Top 100 Reasoning Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | PageIndex | 35,507 | 3,128 | Python | 32 | 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG | 2026-09-03 |
| 2 | WeKnora | 21,283 | 3,077 | Go | 386 | Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. | 2026-09-03 |
| 3 | clip-as-service | 12,835 | 2,067 | Python | 290 | 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP | 2024-01-23 |
| 4 | HRM | 12,631 | 1,825 | Python | 61 | Hierarchical Reasoning Model Official Release | 2026-03-31 |
| 5 | semantica | 11,880 | 1,339 | Python | 60 | Graph-Native Infrastructure for Context and Accountable AI Systems | 2026-09-03 |
| 6 | KAG | 9,037 | 714 | Python | 165 | 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 |
| 7 | dsh-routing-suite | 7,058 | 148 | JavaScript | 31 | dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23). | 2026-09-02 |
| 8 | Awesome-LLM-Strawberry | 6,901 | 368 | - | 8 | A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques. | 2025-12-17 |
| 9 | pyspur | 5,781 | 429 | TypeScript | 29 | A visual playground for agentic workflows: Iterate over your agents 10x faster | 2026-06-29 |
| 10 | deepreasoning | 5,364 | 437 | Rust | 51 | A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models. | 2025-10-07 |
| 11 | Search-R1 | 5,363 | 484 | Python | 27 | Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL | 2025-11-13 |
| 12 | node-DeepResearch | 5,223 | 460 | TypeScript | 48 | Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget) | 2026-05-01 |
| 13 | reasoning-from-scratch | 5,146 | 801 | Jupyter Notebook | 2 | Implement a reasoning LLM in PyTorch from scratch, step by step | 2026-09-01 |
| 14 | capsule-react | 5,053 | 13 | Rust | 0 | ReAct loop coordinator. Stateless state machine for reasoning-and-action cycle. Part of Unicity AOS. | 2026-07-09 |
| 15 | ARC-AGI | 4,824 | 724 | JavaScript | 30 | The Abstraction and Reasoning Corpus | 2025-04-04 |
| 16 | tree-of-thoughts | 4,592 | 376 | 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 |
| 17 | typedb | 4,439 | 371 | Rust | 284 | TypeDB: Built for systems, not records | 2026-09-03 |
| 18 | probability | 4,432 | 1,126 | Jupyter Notebook | 648 | Probabilistic reasoning and statistical analysis in TensorFlow | 2026-08-06 |
| 19 | GLM-4.5 | 4,423 | 476 | Python | 27 | GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | 2026-02-01 |
| 20 | g1 | 4,174 | 357 | Python | 0 | g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains | 2025-12-30 |
| 21 | ReAct | 4,151 | 401 | Jupyter Notebook | 4 | [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models | 2024-02-06 |
| 22 | mm-cot | 3,985 | 333 | Python | 44 | Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated) | 2024-06-12 |
| 23 | simpleRL-reason | 3,873 | 284 | Python | 33 | Simple RL training for reasoning | 2025-12-23 |
| 24 | PhiCookBook | 3,820 | 518 | 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 ... | 2026-09-03 |
| 25 | ReAgent | 3,712 | 529 | Python | 34 | A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.) | 2026-09-01 |
| 26 | Awesome-LLM-Reasoning | 3,681 | 213 | - | 5 | From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓 | 2026-04-20 |
| 27 | Rapid-MLX | 3,649 | 413 | Python | 45 | 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... | 2026-09-04 |
| 28 | DeepSeek-Math | 3,440 | 593 | Python | 39 | DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | 2024-04-15 |
| 29 | terminusdb | 3,402 | 151 | Prolog | 12 | TerminusDB is a distributed, collaborative database designed for building, sharing, versioning, and reasoning on structured data. | 2026-09-03 |
| 30 | pgmpy | 3,325 | 1,150 | Python | 455 | Python Toolkit for Causal and Probabilistic Reasoning | 2026-08-19 |
| 31 | MiniMax-M1 | 3,181 | 282 | Python | 29 | MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. | 2025-07-07 |
| 32 | Skywork-R1V | 3,169 | 282 | Python | 36 | Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning. | 2026-07-29 |
| 33 | AI-Agents-Projects-Tutorials | 2,889 | 619 | Jupyter Notebook | 5 | Multi-agent systems, memory, planning, reasoning loops | 2026-08-24 |
| 34 | RAGEN | 2,789 | 227 | Python | 28 | Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics | 2026-08-23 |
| 35 | chain-of-thought-hub | 2,774 | 144 | Jupyter Notebook | 18 | Benchmarking large language models' complex reasoning ability with chain-of-thought prompting | 2024-08-04 |
| 36 | LISA | 2,673 | 207 | Python | 115 | Project Page for "LISA: Reasoning Segmentation via Large Language Model" | 2025-02-16 |
| 37 | Cradle | 2,580 | 266 | 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 |
| 38 | griptape | 2,575 | 254 | Python | 60 | Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory. | 2026-09-03 |
| 39 | Awesome-LLM-Post-training | 2,536 | 169 | Python | 7 | Awesome Reasoning LLM Tutorial/Survey/Guide | 2026-07-27 |
| 40 | Awesome-RL-for-LRMs | 2,484 | 133 | TeX | 3 | A Survey of Reinforcement Learning for Large Reasoning Models | 2026-08-20 |
| 41 | Pentest-Swarm-AI | 2,451 | 459 | Go | 15 | Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring... | 2026-08-31 |
| 42 | GLM-V | 2,380 | 182 | Python | 13 | GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | 2026-09-02 |
| 43 | llm-reasoners | 2,343 | 205 | Python | 31 | A library for advanced large language model reasoning | 2025-06-10 |
| 44 | graph-rag-agent | 2,332 | 322 | Python | 33 | 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 |
| 45 | open-thoughts | 2,330 | 194 | Python | 6 | Fully open data curation for reasoning models | 2025-12-02 |
| 46 | MiMo | 2,308 | 106 | Python | 70 | MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining | 2025-06-05 |
| 47 | penecho | 2,271 | 286 | JavaScript | 6 | Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning. | 2026-08-28 |
| 48 | Step1X-Edit | 2,258 | 102 | 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 |
| 49 | Embodied_AI_Paper_List | 2,161 | 151 | - | 1 | [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI | 2026-06-10 |
| 50 | mcp-shrimp-task-manager | 2,151 | 256 | JavaScript | 38 | 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 |
| 51 | antigravity-cli | 2,144 | 196 | - | 619 | Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal. | 2026-09-03 |
| 52 | LLaVA-CoT | 2,132 | 81 | Python | 0 | [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning | 2025-12-12 |
| 53 | Chain-of-ThoughtsPapers | 2,104 | 143 | - | 0 | A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models". | 2023-10-05 |
| 54 | auto-cot | 2,048 | 192 | Jupyter Notebook | 8 | Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated) | 2024-03-13 |
| 55 | continuous-thought-machines | 2,025 | 309 | Python | 3 | Continuous Thought Machines, because thought takes time and reasoning is a process. | 2025-12-29 |
| 56 | alpamayo | 2,014 | 337 | Python | 35 | NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning. | 2026-08-29 |
| 57 | awesome-explainable-graph-reasoning | 1,990 | 137 | - | 0 | A collection of research papers and software related to explainability in graph machine learning. | 2022-04-04 |
| 58 | HRM-Text | 1,946 | 184 | Python | 18 | 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 | PRIME | 1,872 | 115 | Python | 8 | Scalable RL solution for advanced reasoning of language models | 2025-03-18 |
| 60 | openr | 1,854 | 131 | Python | 39 | OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models | 2025-01-17 |
| 61 | SimpleVLA-RL | 1,845 | 121 | Python | 49 | [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning | 2026-01-06 |
| 62 | knowledge-graphs | 1,794 | 298 | JavaScript | 0 | A collection of research on knowledge graphs | 2022-10-07 |
| 63 | WFGY | 1,788 | 165 | 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... | 2026-09-03 |
| 64 | viper | 1,716 | 131 | Jupyter Notebook | 15 | Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning" | 2024-01-29 |
| 65 | ai-agent-papers | 1,631 | 134 | Python | 0 | A collection of AI Agents papers (Updated biweekly) | 2026-08-29 |
| 66 | Seed1.5-VL | 1,586 | 66 | 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 |
| 67 | Vision-R1 | 1,571 | 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 |
| 68 | VibeThinker | 1,568 | 117 | Python | 16 | Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B | 2026-08-14 |
| 69 | Marco-o1 | 1,538 | 81 | Python | 10 | An Open Large Reasoning Model for Real-World Solutions | 2026-06-17 |
| 70 | Awesome_Think_With_Images | 1,502 | 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 |
| 71 | reasoning-gym | 1,501 | 129 | Python | 7 | [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards | 2026-04-17 |
| 72 | protege | 1,493 | 305 | Java | 412 | Protege Desktop | 2026-04-05 |
| 73 | octotools | 1,488 | 186 | Python | 4 | OctoTools: An agentic framework with extensible tools for complex reasoning | 2026-05-02 |
| 74 | WebThinker | 1,467 | 140 | Python | 9 | [NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability | 2025-12-08 |
| 75 | Awesome-RL-based-Reasoning-MLLMs | 1,440 | 70 | - | 7 | This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs! | 2026-08-02 |
| 76 | AgentCPM-GUI | 1,413 | 134 | 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 |
| 77 | haft | 1,389 | 102 | Go | 9 | 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. | 2026-08-11 |
| 78 | math | 1,388 | 116 | Python | 17 | The MATH Dataset (NeurIPS 2021) | 2025-09-06 |
| 79 | KnowLM | 1,386 | 132 | Python | 0 | An Open-sourced Knowledgable Large Language Model Framework. | 2025-01-11 |
| 80 | ThinkSound | 1,378 | 82 | Python | 41 | [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 |
| 81 | MiMo-V2-Flash | 1,367 | 64 | - | 22 | MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model | 2026-01-08 |
| 82 | Awesome-Agentic-Reasoning | 1,356 | 102 | - | 8 | A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models" | 2026-03-09 |
| 83 | HuatuoGPT-o1 | 1,355 | 132 | Python | 26 | Medical o1, Towards medical complex reasoning with LLMs | 2025-01-20 |
| 84 | Awesome-System2-Reasoning-LLM | 1,353 | 79 | Python | 7 | Latest Advances on System-2 Reasoning | 2025-06-08 |
| 85 | pywinassistant | 1,343 | 190 | 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 |
| 86 | LaTeX_OCR_PRO | 1,312 | 240 | 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 |
| 87 | SoftRas | 1,299 | 159 | Python | 55 | Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning" | 2025-11-24 |
| 88 | LuaN1aoAgent | 1,291 | 187 | TypeScript | 4 | LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning. Developed by the Intelligent Offense & Defense Research Group, led by Professor Lu Hu... | 2026-08-24 |
| 89 | understand-r1-zero | 1,274 | 63 | Python | 7 | Understanding R1-Zero-Like Training: A Critical Perspective | 2025-08-27 |
| 90 | youtu-graphrag | 1,256 | 186 | Python | 49 | [ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning | 2026-02-26 |
| 91 | Search-o1 | 1,245 | 108 | Python | 2 | 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025] | 2025-11-17 |
| 92 | Mulberry | 1,243 | 113 | Python | 3 | [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS | 2026-01-16 |
| 93 | Kimi-VL | 1,226 | 92 | - | 40 | Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities | 2025-07-15 |
| 94 | MedRAX | 1,223 | 205 | Python | 5 | MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025 | 2025-10-31 |
| 95 | OpenTSLM | 1,213 | 114 | Python | 6 | OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data | 2026-07-21 |
| 96 | R-KV | 1,211 | 196 | Python | 4 | [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models | 2026-07-20 |
| 97 | Awesome-AI-Memory | 1,197 | 127 | Python | 4 | 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... | 2026-09-02 |
| 98 | chameleon-llm | 1,141 | 82 | Jupyter Notebook | 8 | Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models". | 2023-12-23 |
| 99 | DeepAgent | 1,137 | 141 | Python | 8 | [WWW‘26 Oral🔥] DeepAgent: A General Reasoning Agent with Scalable Toolsets | 2026-04-13 |
| 100 | Prometheus | 1,127 | 77 | Python | 7 | 🧠 Prometheus: A Knowledge-Graph-Driven 🤖 AI Agent that maps 🗺, understands 🧩, and repairs 🛠 complex codebases — not by guessing, but by reasoning. ⚡ | 2026-08-16 |