17 repository-uri
Agents that automate code generation, review, and iterative improvement.
Explore 17 awesome GitHub repositories matching part of an awesome list · Code Refinement. Refine with filters or upvote what's useful.
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
Open platform for generalist AI software developers.
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
Allows users to incrementally update the user interface by refining natural language instructions.
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
Provides a mechanism for users to iteratively refine and edit natural language prompts to improve generated code quality.
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
Enables rapid iteration of instructions by cloning and editing previous prompts.
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
Teaches the iterative process of refining natural language instructions to improve the quality of model-generated outputs.
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
Updates generated code snippets iteratively based on new prompt instructions or error messages.
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
Analyzes performance failures to rewrite instructions and improve accuracy for classification tasks.
LLM4Decompile este un set de instrumente și un framework pentru traducerea din binar în cod sursă. Utilizează modele de limbaj mari (LLM) pentru a transforma codul mașină în cod sursă lizibil și pentru a recupera logica originală a executabilelor compilate. Proiectul include un pipeline specializat pentru generarea de seturi de date de antrenament sintetice prin convertirea codului sursă în perechi de assembly. Oferă un framework de fine-tuning pentru a optimiza modelele de deep learning pe aceste seturi de date binar-la-sursă, crescând acuratețea recuperării codului. Sistemul dispune, de asemenea, de capabilități pentru rafinarea pseudo-codului decompilat. Acest proces se concentrează pe restaurarea scheletului structural și a numelor variabilelor dintr-un binar pentru a îmbunătăți lizibilitatea logicii dezasamblate.
Provides iterative refinement of raw decompilation output to correct syntax and improve variable names.
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
Rewrites vague user inputs into structured prompts to improve the precision and quality of model outputs.
OpenEvolve este un framework de algoritmi evolutivi care utilizează modele de limbaj mari pentru a descoperi și optimiza autonom algoritmi de programare. Funcționează ca un motor de descoperire a algoritmilor și instrument de căutare a codului, evoluând populații de programe candidate pentru a găsi implementări eficiente și optimizări specifice hardware-ului. Sistemul tratează atât codul, cât și instrucțiunile de sistem ca entități evolutive, utilizând un optimizator automat de prompt-uri pentru a rafina iterativ performanța modelului. Menține stabilitatea căutării prin gestionarea populației bazată pe nișe pentru a păstra diversitatea și utilizează un mecanism de feedback în buclă închisă care injectează erorile de runtime și log-urile înapoi în procesul de generare pentru repararea autonomă a bug-urilor. Framework-ul include, de asemenea, un orchestrator de agenți care agregă răspunsurile de la mai multe API-uri de modele folosind logică ponderată și strategii de fallback. Pentru a susține calculul științific, implementează execuția deterministă prin gestionarea unor semințe aleatorii (random seeds) consistente în toate componentele stochastice. Proiectul oferă un tablou de bord interactiv pentru vizualizarea progresului evoluției și a metricilor de performanță în timp real.
Open-source evolutionary coding agent.
vibesdk este o platformă și un framework de dezvoltare software agentic conceput pentru a coordona agenți autonomi care scriu, depanează și rafinează aplicații full-stack din limbaj natural. Servește ca un orchestrator de aplicații cloud-native și un framework de generare de cod bazat pe LLM care convertește prompturile în cod funcțional prin conversații iterative și comportamente ale agenților în mai multe faze. Proiectul se remarcă prin furnizarea unui toolchain complet pentru construirea platformelor de dezvoltare AI. Aceasta include capacitatea de a integra diverși furnizori de modele, de a construi toolkit-uri LLM personalizate și de a gestiona întregul ciclu de viață al aplicațiilor generate de AI printr-un toolchain de deployment serverless și un SDK TypeScript programatic. Platforma acoperă o gamă largă de capabilități, inclusiv orchestrarea sandbox-urilor AI pentru execuție izolată și previzualizări live, sisteme de fișiere virtuale susținute de Git pentru urmărirea versiunilor și deployment automat în cloud pe platforme serverless. De asemenea, încorporează sisteme pentru gestionarea schemelor de baze de date, criptarea ierarhică a secretelor și sincronizarea stării în timp real prin WebSockets. Utilizatorii pot gestiona fluxurile de lucru ale proiectului printr-o interfață de linie de comandă sau programatic folosind SDK-ul furnizat.
Implements a conversational interface for iterating on features and fixing errors through AI-driven code refinement.
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
Improves the quality of generated source code by cycling through generation, execution, and correction workflows.
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Framework for 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.
Iterative code refinement using self-feedback.
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.…
Multi-agent code generation with iterative testing.
Code and data for paper "Self-Evolving Multi-Agent Collaboration Networks for Software Development".
Self-evolving multi-agent networks for software development.
please visit: https://zenodo.org/records/11666403
Autonomous communicative agents for code review.