Awesome GitHub RepositoriesComplex Problem Solving

DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing and internal monologues to solve complex mathematical and logical problems by breaking tasks into sequential, verifiable thought processes. The model is developed using reinforcement learning to optimize reasoning patterns and verify logical steps. It employs a distillation process to transfer these high-performance logic capabilities from a large teacher model into smaller, computationally efficient versions. The training framework incorporates group relative policy optimiz

Qwen2.5 is a suite of large language model foundation models designed for natural language generation, code production, and complex mathematical reasoning. The project encompasses a multilingual language model capable of processing dozens of languages and a specialized code generation model for technical problem solving and debugging. The framework is distinguished by its long context capabilities, enabling the analysis of massive inputs ranging from 256K up to 1 million tokens. It further functions as an agentic framework, utilizing standardized templates and parsers to execute autonomous wo

Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level

gpt-oss is an open-weight large language model and reasoning engine designed for complex reasoning and agentic workflows. It functions as an AI agent framework and model serving API, allowing for local deployment and the hosting of standardized interfaces to expose model completions and internal reasoning processes. The project distinguishes itself as a quantized inference engine, utilizing tensor parallelism and weight quantization to run high-parameter models on limited hardware. It features a reasoning model that employs chain-of-thought processing to solve multi-step logical tasks. The s

Qwen2.5-VL este un transformer multimodal autoregresiv conceput pentru a procesa secvențe intercalate de token-uri de text și vizuale. Acesta integrează embedding-urile caracteristicilor vizuale într-un spațiu comun de model de limbaj pentru a efectua raționamente cross-modale și a genera răspunsuri coerente sau cod de layout structurat. Proiectul se distinge prin maparea viziune-limbaj-acțiune, permițându-i să perceapă interfețele vizuale și să traducă acea percepție în comenzi acționabile pentru operarea ecranelor digitale și a hardware-ului robotic. Utilizează codificarea imaginilor cu rezoluție dinamică și indexarea video pe cadre temporale pentru a gestiona dimensiuni diverse ale imaginilor și secvențe vizuale de lungă durată. Modelul acoperă o suprafață largă de capabilități, inclusiv recunoașterea optică a caracterelor multilingve pentru digitizarea documentelor, ancorarea spațială pentru localizarea obiectelor prin bounding boxes și analiza conținutului video de lungă durată. De asemenea, suportă raționamentul matematic multimodal pentru a rezolva probleme folosind grafice și diagrame și își extinde înțelegerea la o lungime de context de un milion de token-uri.

Qwen2-VL is a multimodal large language model and vision language model designed to process and reason across text, images, and video content. It functions as a visual reasoning engine and a visual agent framework, capable of interpreting visual data to perform object detection, document parsing, and spatial reasoning. The model is distinguished by its ability to act as a video understanding model, processing hour-long videos with second-level indexing and event recall. It further differentiates itself through a visual agent capability that interacts with software interfaces and robotic hardw

PUA is an agentic workflow orchestrator and behavioral governance tool designed to enhance the reliability and autonomy of AI coding assistants. It functions as a prompting framework and extension that implements strict engineering standards and verification requirements to prevent hallucinations and premature task completion. The project distinguishes itself through high-agency enforcement mechanisms, including escalating prompt pressure and failure-driven recovery loops that automatically pivot problem-solving strategies after repeated errors. It utilizes a diagnosis-first workflow that man

ChatGLM3 is an open-weights large language model designed for bilingual conversational interactions in English and Chinese. It functions as a tool-augmented system capable of calling external functions and executing internal code to resolve complex tasks. The model utilizes four-bit quantization to reduce memory requirements, enabling inference on consumer hardware and diverse processing units including GPUs and CPUs. It features an expanded context window for processing and summarizing long documents and includes a supervised fine-tuning pipeline for adapting the model to specialized domains

Kimi-K2 is a conversational AI engine and reasoning framework designed for text generation, advanced problem solving, and coding tasks. It functions as a tool-augmented language model capable of producing human-like chat responses through a compatible model interface. The system utilizes a reasoning-optimized architecture that separates standard conversational flow from deep logical processing. This allows the model to execute autonomous tasks by invoking external functions and calling APIs to retrieve real-time data. The project supports structured JSON output parsing for function-call inte

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

WizardLM is a large language model and instruction-tuning framework designed to execute sophisticated coding, mathematical, and conversational tasks. It functions as an AI system for mathematical reasoning and code generation, as well as a synthetic dataset generator used to train other language models. The project is distinguished by its evolutionary instruction tuning, which uses a method to rewrite simple instructions into complex tasks. This process expands training dataset difficulty and produces a high volume of open-domain tasks across various difficulty levels. The system covers capa

This project is a comprehensive AI infrastructure that combines an LLM agent orchestration framework, an autonomous research system, and a local AI environment. It centers on the creation of a personal knowledge graph and a programmatic prompt engineering library to provide long-term memory and optimized reasoning for artificial intelligence tasks. The system is distinguished by its ability to compose multi-agent teams using specialized personas and deterministic skills to execute complex workflows. It features an autonomous research pipeline capable of deep investigations and adversarial ana

This project is a Python collection of algorithms and data structures that implement the concepts from the Artificial Intelligence: A Modern Approach textbook. It serves as an educational resource for learning core artificial intelligence concepts through the implementation of classic algorithms for searching, logic, and problem solving. The repository functions as an automated reasoning toolset for managing knowledge bases, a game theory engine for calculating optimal moves in competitive games, and a search and optimization library. It provides specialized frameworks for deriving logical co

XAgent is an autonomous agent system that decomposes complex goals into sequential subtasks for execution via a planner and actor model. It functions as a collaboration framework that integrates human-in-the-loop workflows, allowing users to provide real-time guidance and missing information during the automation process. The system features a containerized tool sandbox to isolate the execution of shells and browsers, ensuring system safety and consistency. It includes a state-based execution recorder that captures snapshots of agent runs to enable the exact reproduction of specific task sequ

Context-Engineering is a prompt engineering framework and cognitive architecture for large language models. It provides a set of patterns and methodologies for designing structured prompts and modular reasoning flows that decompose complex tasks into specialized, step-by-step problem solving templates. The project distinguishes itself through stateful prompt management and context window optimization. It maintains persistent memory across multiple interaction turns by compressing conversation history into compact internal state cells and employs techniques to maximize information density per

LARK is a development toolkit for training, fine-tuning, and deploying large language models and multimodal models based on PaddlePaddle. It functions as a comprehensive framework that includes an LLM training orchestrator, an inference server, and a multimodal model framework for processing text, image, and video inputs. The project features a retrieval-augmented generation system for building conversational applications that integrate web search and private knowledge bases. It provides specific capabilities for multimodal reasoning and complex logic, enabling the extraction of structured da

ERNIE is a development toolkit for training, fine-tuning, and deploying large language models built on the PaddlePaddle deep learning platform. It provides a comprehensive suite of core components, including an inference server for vision and language models, a training and fine-tuning toolkit, and a framework for building retrieval-augmented generation systems using private knowledge bases. The project features multimodal AI models capable of reasoning across text, images, and video to perform complex visual understanding and information extraction. It distinguishes itself through specialize

LogicStack-LeetCode is a curated repository of solved algorithm problems and data structure implementations, primarily drawn from the LeetCode platform. Its core identity is a structured collection of solutions designed to support technical interview preparation and competitive programming practice, with each solution accompanied by complexity analyses to help engineers understand performance trade-offs. The repository distinguishes itself through its breadth of coverage across fundamental algorithmic patterns and data structures. It includes implementations for array manipulation, string pro

This project is a comprehensive Lisp AI implementation library that provides reference implementations for various artificial intelligence paradigms and symbolic algorithms. It functions as a multi-purpose toolkit containing a logic programming engine, a natural language processing suite, and a symbolic mathematics toolkit. The library is distinguished by its diverse architectural frameworks, including a Prolog-style execution engine that uses unification and goal-driven backtracking, and a system for simulating human decision-making through expert system shells and certainty factors. It also

InternLM is a large language model and a comprehensive suite of weights designed for text generation and complex reasoning. It functions as an inference engine for serving responses, a fine-tuning framework for adjusting model weights, and a platform for building autonomous AI agents. The system is capable of processing long-context input sequences up to one million tokens for document analysis. It employs chain-of-thought reasoning to solve knowledge-intensive tasks by generating intermediate logic steps before producing a final answer. The project covers model weight optimization through s