Awesome GitHub RepositoriesCode Refinement

OpenHands is an autonomous AI software engineer and coding assistant designed to execute software engineering tasks by interacting directly with codebases and development environments. It functions as a platform for running AI agents that can write code and manage files to automate complex development workflows. The system distinguishes itself through a container-based execution environment that isolates agent actions within a sandboxed Linux environment. It employs an autonomous agent loop of observation, planning, and action, supported by a standardized communication protocol that allows it

OpenUI is an AI design sandbox and natural language prototyping tool used to generate and render live user interface components from text descriptions. It functions as an LLM UI generator that translates natural language into executable HTML and CSS code. The system provides a pipeline for iterative refinement, allowing users to update existing interfaces by feeding previous code versions and new instructions back into the model. It also acts as a frontend framework converter, transforming HTML markup into different library formats to maintain styling consistency across various web frameworks

bolt.new is an AI-powered full-stack web builder and browser-based IDE that generates, edits, and deploys web applications using natural language prompts. It functions as an AI-driven application orchestrator, managing the entire development lifecycle through a chat interface. The platform distinguishes itself by integrating a WebAssembly-based runtime and virtual terminal emulation directly in the browser. This allows an AI agent to execute tool calls, manage a virtual filesystem, install packages, and run servers without requiring a local development environment. The system covers a compre

KeepChatGPT is a browser extension designed to enhance the ChatGPT web experience by acting as a session manager, UI optimizer, and privacy guard. It focuses on maintaining active connections to prevent session timeouts and improving the overall interface for better readability and organization. The project distinguishes itself through privacy and security features that block tracking telemetry and use regular expressions to mask sensitive data before it is sent. It also includes tools to mitigate conversation auditing and bypass bot verification challenges to reduce the risk of account restr

llm-universe is a structured learning resource and technical guide focused on the development of large language model applications. It serves as a curriculum for mastering model orchestration, the creation of autonomous conversational agents, and the implementation of retrieval-augmented generation systems. The project provides detailed instructions on connecting model APIs with memory and tools to create execution chains. It specifically covers the construction of retrieval pipelines, including the process of cleaning raw documents, generating embeddings, and integrating vector databases to

This project is an AI software engineering tool and framework for building autonomous coding agents. It provides a system for automating program synthesis and bug fixing by integrating large language models with codebase analysis and iterative refinement loops. The framework features an agentic development server that exposes task execution interfaces to remote agents through a structured protocol. This allows for the remote execution of development tasks and the embedding of autonomous program synthesis capabilities into external software projects. The toolset covers AI-driven project scaff

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

LLM4Decompile es un conjunto de herramientas y framework para la traducción de código binario a código fuente. Utiliza modelos de lenguaje de gran tamaño (LLM) para transformar código máquina en código fuente legible y recuperar la lógica original de ejecutables compilados. El proyecto incluye un pipeline especializado para generar datasets de entrenamiento sintéticos convirtiendo código fuente en pares de ensamblador. Proporciona un framework de fine-tuning para optimizar modelos de deep learning en estos datasets de binario a fuente, aumentando la precisión de la recuperación de código. El sistema también cuenta con capacidades para refinar pseudocódigo descompilado. Este proceso se centra en restaurar el esqueleto estructural y los nombres de variables de un binario para mejorar la legibilidad de la lógica desensamblada.

ChatGPT-AutoExpert is an AI prompt engineering framework and persona management system designed to improve the technical accuracy and nuance of large language model outputs. It provides a collection of curated system prompts and custom instructions to refine user queries and remove conversational filler. The system employs a persona framework to assign specialized expert roles based on the request context. It utilizes a command shortcut system that maps short text sequences to complex instructional sets, enabling the rapid execution of repetitive tasks. For software development, the project

OpenEvolve es un framework de algoritmos evolutivos que utiliza modelos de lenguaje de gran tamaño para descubrir y optimizar algoritmos de programación de forma autónoma. Funciona como un motor de descubrimiento de algoritmos y herramienta de búsqueda de código, evolucionando poblaciones de programas candidatos para encontrar implementaciones eficientes y mejoras de velocidad específicas para el hardware. El sistema trata tanto el código como las instrucciones del sistema como entidades evolutivas, utilizando un optimizador de prompts automatizado para refinar iterativamente el rendimiento del modelo. Mantiene la estabilidad de la búsqueda mediante la gestión de poblaciones basada en nichos para preservar la diversidad y emplea un mecanismo de retroalimentación de bucle cerrado que inyecta errores de tiempo de ejecución y registros de vuelta al proceso de generación para la corrección autónoma de errores. El framework también incluye un orquestador de agentes que agrega respuestas de múltiples APIs de modelos utilizando lógica ponderada y estrategias de respaldo. Para apoyar la computación científica, implementa la ejecución determinista gestionando semillas aleatorias consistentes en todos los componentes estocásticos. El proyecto proporciona un panel interactivo para visualizar el progreso de la evolución y métricas de rendimiento en tiempo real.

vibesdk es una plataforma y framework de desarrollo de software agentico diseñado para coordinar agentes autónomos que escriben, depuran y refinan aplicaciones full-stack a partir de lenguaje natural. Sirve como un orquestador de aplicaciones cloud-native y un framework de generación de código potenciado por LLM que convierte prompts en código funcional a través de conversaciones iterativas y comportamientos de agentes multifase. El proyecto se distingue por proporcionar una cadena de herramientas completa para construir plataformas de desarrollo de IA. Esto incluye la capacidad de integrar varios proveedores de modelos, construir kits de herramientas LLM personalizados y gestionar todo el ciclo de vida de las aplicaciones generadas por IA a través de una cadena de herramientas de despliegue serverless y un SDK de TypeScript programático. La plataforma cubre una amplia gama de capacidades, incluyendo orquestación de sandbox de IA para ejecución aislada y vistas previas en vivo, sistemas de archivos virtuales respaldados por Git para el seguimiento de versiones y despliegue automático en la nube a plataformas de workers serverless. También incorpora sistemas para la gestión de esquemas de bases de datos, cifrado jerárquico de secretos y sincronización de estado en tiempo real mediante WebSockets. Los usuarios pueden gestionar los flujos de trabajo del proyecto a través de una interfaz de línea de comandos o programáticamente utilizando el SDK proporcionado.

AlphaCodium is an LLM code generation framework and automated programming benchmark designed to solve programming problems through iterative generation and testing. It functions as an iterative code refinement system that improves the precision of generated code by comparing outputs against expected results and re-prompting the model. The project implements a flow engineering pipeline, using a structured sequence of prompting stages to refine code through a cycle of generation, evaluation, and correction. This approach allows the system to process programming datasets and measure the accuracy

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

With Self-Refine, LLMs can generate feedback on their work, use it to improve the output, and repeat this process.

AgentCoder is a novel multiagent-code generation framework that leverages the power of large language models (LLMs) to enhance the effectiveness of code generation. The framework consists of three specialized agents: the programmer agent, the test designer agent, and the test executor agent.…

Code and data for paper "Self-Evolving Multi-Agent Collaboration Networks for Software Development".

please visit: https://zenodo.org/records/11666403