Awesome GitHub RepositoriesIterative Refinement Workflows

OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It

Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated

Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

Plandex is an AI-powered software development platform that operates as a command-line interface to manage complex, long-running coding tasks. It functions as an automated agent that decomposes high-level programming objectives into granular, actionable steps, executing multi-file code changes directly within a local project environment. The system distinguishes itself through a state-machine-based execution model that tracks progress across iterative development cycles. By utilizing context-aware code indexing and an iterative feedback loop, the tool refines generated code through successive

This project is a Python-based educational framework designed to simulate reinforcement learning algorithms and environments. It serves as a platform for reproducing classic textbook examples, allowing users to study agent behavior, policy improvement, and the fundamental mechanics of decision-making in controlled settings. The library provides implementations for core reinforcement learning concepts, including temporal difference learning, Monte Carlo episode sampling, and tabular value function approximation. It enables the analysis of specific algorithmic behaviors, such as identifying and

AutoResearchClaw is an agentic system designed to automate the scientific research process. It functions as an autonomous research agent and workflow automator that manages the entire lifecycle of a project, from initial hypothesis generation and literature review to experimental execution and the production of LaTeX-formatted academic papers. The system distinguishes itself through a multi-agent research pipeline that utilizes structured debates for hypothesis refinement and peer review. It employs a branch-and-merge architecture to explore parallel research directions and integrates human-i

PentestGPT is an autonomous security testing framework that leverages large language models to plan, execute, and coordinate end-to-end penetration testing engagements. By functioning as an autonomous agent, the system automates the entire testing lifecycle, from initial reconnaissance and vulnerability analysis to the generation of custom exploits and the execution of post-exploitation tasks. The platform distinguishes itself through a multi-agent orchestration system that coordinates specialized AI agents to collaborate on complex, multi-stage attack chains. It integrates multimodal context

Unity MCP is a plugin that connects the Unity Editor to AI assistants through the Model Context Protocol, enabling natural language control over scene manipulation, object creation, and editor workflows. It allows developers to generate C# scripts, modify GameObjects and components, create UI layouts, and manage assets by issuing commands through an AI interface, effectively turning the editor into a conversational development environment. The plugin distinguishes itself through a comprehensive automation system that can execute multi-step tasks from a design document, record and replay edito

This project is an automated prompt engineering and optimization tool designed to iteratively create, test, and refine prompts using a language model to improve output quality. It functions as a framework for generating candidate prompts and ranking their performance through correctness matching and ELO-based ratings. The system includes capabilities for model distillation, generating high-quality example pairs from frontier models to create training data for smaller models. It also provides tools to condense prompts for smaller models and transform instruction-tuned prompts into completion-b

Paper-qa is a retrieval augmented generation system designed for question answering and analysis of scientific literature and technical documents. It functions as an LLM-powered research assistant that extracts grounded answers and summaries with citations from a document library. The system utilizes an agentic RAG orchestrator to iteratively refine search queries and gather evidence through multi-step tool calling. It features a multimodal document parser that extracts text, tables, and images from PDFs, alongside a vector-based indexer that embeds and caches document libraries for efficient

mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist

This project is a computer vision system for object segmentation and tracking across images and videos. It employs models capable of identifying and masking objects using text prompts, bounding boxes, click points, or image exemplars. The system differentiates itself through memory-based video tracking and shared-memory architectures that maintain consistent object identities over time. It supports multi-object processing in single computation passes to increase frame throughput and utilizes iterative refinement to correct segmentation boundaries through sequential prompts. The software also

SAMURAI is a zero-shot visual tracking model that adapts the Segment Anything architecture for video object segmentation. It uses a first-frame prompt, such as a bounding box or mask, to initialize tracking, then employs a motion-aware memory mechanism that stores and updates temporal motion features across frames to guide mask refinement. An online memory update strategy continuously refreshes this memory with new frame predictions, while temporal motion encoding computes optical flow between consecutive frames to inform object boundary and occlusion handling. The system is designed for real

Track-Anything is an AI-driven video object segmentation and tracking system. It utilizes the Segment Anything Model to isolate and mask multiple objects across video frames, providing tools for automated mask propagation and background-filling inpainting. The system distinguishes itself through a multi-object segmentation pipeline that can follow several distinct targets simultaneously. It includes a video inpainting utility to remove tracked objects and replace them with synthesized background content, as well as temporal mask refinement to correct tracking drift. The project covers broad

SkyReels-V2 is a video generation system that creates, extends, and refines video clips from text descriptions, images, or both. It operates as a diffusion-based video generation model that can produce videos of any duration by denoising frames sequentially, with each new frame conditioned on the ones that came before it. The system supports generating videos from scratch using text prompts, starting from a single image and producing subsequent frames, or constraining both the first and last frames to match user-provided images. What distinguishes SkyReels-V2 is its combination of infinite-le

يوفر هذا المشروع منهجيات وأدلة لهندسة الأوامر (Prompt Engineering) المهيكلة، وسير العمل التوليدي، واستراتيجيات توليد الصور المتخصصة. يعمل كإطار عمل لتحسين المدخلات لنماذج اللغات الكبيرة (LLM) عبر مهام البرمجة والكتابة والتحليل، بالإضافة إلى كونه مكتبة تقنيات للتحكم في نماذج الانتشار (Diffusion Models). يتميز المشروع بإطار عمل لتصميم البرمجيات مدعوم بالذكاء الاصطناعي يحول متطلبات الأعمال إلى بنيات تقنية وأكواد برمجية باستخدام التوجيه الموجه بالمجال (Domain-Driven Prompting). كما ينفذ أنماط سير عمل الذكاء الاصطناعي التوليدي التي تستخدم خطوط أنابيب الأوامر المتسلسلة والأطر المعرفية لضمان مخرجات نموذجية يمكن التنبؤ بها. تغطي قدرات المشروع هندسة البرمجيات من خلال نمذجة واجهات برمجة التطبيقات (API) الموجهة بالمجال وتوليد لغات خاصة بالمجال (DSL). كما تمتد لتشمل توليد الصور، بما في ذلك الربط الهيكلي للصور، وتدريب النماذج المخصصة، والتحسين التكراري للرسم الداخلي (Inpainting) لتصحيح العيوب البصرية. تم تنفيذ المشروع كمجموعة من دفاتر Jupyter Notebooks.

Co-tracker is a PyTorch point tracking framework and dense point tracking model designed to map the motion of individual pixels throughout a video. It functions as a video pixel tracker that predicts point trajectories and visibility masks across sequences of video frames. The project includes a computer vision training pipeline that utilizes teacher-student knowledge distillation. This allows for the generation of pseudo-labels from unannotated real video data to fine-tune pre-trained models and reduce the gap between synthetic and real data environments. The framework provides capabilities

Adetailer is a Stable Diffusion inpainting extension and automated detail enhancer that identifies specific image regions to improve quality through targeted inpainting. It functions as an AI image masking tool that uses detection models to create precise masks for automated image editing. The system distinguishes itself by integrating structural guides, such as depth and pose, to constrain the inpainting process and maintain anatomical consistency. It also supports object-specific prompt assignment, allowing unique text instructions to be mapped to multiple detected objects within a single i