awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoAcerca deCómo clasificamosPrensaServidor MCP
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
madaan avatar

madaan/self-refine

0
View on GitHub↗
806 estrellas·70 forks·Python·Apache-2.0·4 vistasselfrefine.info↗

Self Refine

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

Features

  • Agent Refinement - Iterative refinement of outputs using self-generated feedback.
  • Reasoning And Planning - Iterative refinement framework using self-feedback mechanisms.
  • Code Refinement - Iterative code refinement using self-feedback.

Historial de estrellas

Gráfico del historial de estrellas de madaan/self-refineGráfico del historial de estrellas de madaan/self-refine

Búsqueda con IA

Explora más repositorios increíbles

Describe lo que necesitas en lenguaje sencillo: la IA clasifica miles de proyectos open-source curados por relevancia.

Start searching with AI

Alternativas open-source a Self Refine

Proyectos open-source similares, clasificados según cuántas características comparten con Self Refine.
  • codium-ai/alphacodiumAvatar de Codium-ai

    Codium-ai/AlphaCodium

    3,945Ver en GitHub↗

    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

    Pythonbroader-impactscode-generationflow-engineering
    Ver en GitHub↗3,945
  • smol-ai/developerAvatar de smol-ai

    smol-ai/developer

    12,188Ver en GitHub↗

    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

    Python
    Ver en GitHub↗12,188
  • cloudflare/vibesdkAvatar de cloudflare

    cloudflare/vibesdk

    5,094Ver en GitHub↗

    vibesdk is an agentic software development platform and framework designed to coordinate autonomous agents that write, debug, and refine full-stack applications from natural language. It serves as a cloud-native application orchestrator and an LLM-powered code generation framework that converts prompts into functional code through iterative conversations and multi-phase agent behaviors. The project distinguishes itself by providing a complete toolchain for building AI development platforms. This includes the ability to integrate various model providers, construct custom LLM toolkits, and mana

    TypeScript
    Ver en GitHub↗5,094
  • amazon-science/mm-cotAvatar de amazon-science

    amazon-science/mm-cot

    3,990Ver en GitHub↗

    This project is a multimodal large language model reasoning framework designed to train and evaluate models in performing chain-of-thought reasoning across text and image data. It provides a reasoning engine and training system that enable vision-language models to generate step-by-step logical rationales and final answers for complex queries. The framework utilizes a two-stage training pipeline that decouples the generation of logical justifications from final answer inference. It transforms visual data into descriptive text through image captioning and uses vision-transformer feature extrac

    Python
    Ver en GitHub↗3,990
Ver las 23 alternativas a Self Refine→

Preguntas frecuentes

¿Qué hace madaan/self-refine?

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

¿Cuáles son las características principales de madaan/self-refine?

Las características principales de madaan/self-refine son: Agent Refinement, Reasoning And Planning, Code Refinement.

¿Qué alternativas de código abierto existen para madaan/self-refine?

Las alternativas de código abierto para madaan/self-refine incluyen: smol-ai/developer — This project is an AI software engineering tool and framework for building autonomous coding agents. It provides a… cloudflare/vibesdk — vibesdk is an agentic software development platform and framework designed to coordinate autonomous agents that write,… codium-ai/alphacodium — AlphaCodium is an LLM code generation framework and automated programming benchmark designed to solve programming… amazon-science/mm-cot — This project is a multimodal large language model reasoning framework designed to train and evaluate models in… codelion/openevolve — OpenEvolve is an evolutionary algorithm framework that uses large language models to autonomously discover and… ber666/rap.