Awesome GitHub RepositoriesSelf-Correction Loops

Thinking-Claude is a browser extension and reasoning interface designed to compel large language models to perform deep inner monologues before delivering final responses. It functions as a thought process formatter that organizes internal AI reasoning into a structured format. The tool uses systematic reasoning prompts and instruction-based injection to force models through a multi-step verification process. This ensures the AI executes a recursive loop of reasoning and self-correction prior to emitting an answer. To manage this output, the project employs client-side response interception

TinyZero is a reinforcement learning framework and implementation designed to train language models to develop reasoning and self-verification abilities. It provides a training pipeline to optimize model performance on mathematical and logical tasks. The project serves as a minimal reproduction of the DeepSeek R1 architectural and training approach. It focuses on creating reasoning models that can solve structured problems through autonomous chain-of-thought discovery. The framework incorporates group relative policy optimization and reward-based self-correction to improve accuracy on logica

This project is a collection of architectural templates and design patterns for building autonomous AI agents. It provides a framework for transitioning from simple prompt-response loops to goal-oriented systems that utilize structural patterns to increase autonomy and improve the reliability of complex task completion. The framework focuses on reasoning orchestration, specifically through the implementation of reflection and self-correction cycles. It enables the coordination of specialized agents via task delegation and state sharing to solve complex problems. The architectural surface cov

Learn_Prompting 是一个专注于提示词工程（prompt engineering）的教育项目，提供了制作有效输入并提高生成式 AI 输出质量所需的原则和技术。 该项目涵盖了增强推理、可靠性和输出质量的高级提示词策略。这包括任务分解、思维链（chain-of-thought）推理，以及使用少样本（few-shot）和零样本（zero-shot）引导的技术。它还通过研究提示词注入（prompt hacking）、漏洞分析和隐私审计来解决模型安全问题，以防止敏感数据泄露。 其范围扩展到生成式 AI 在多种媒体和工作流中的实际应用，包括文本生成、照片级图像创建和视听制作。它进一步涵盖了自主智能体（autonomous agents）的开发、AI 辅助编程，以及用于营销和通信的业务工作流自动化。 该项目为模型优化、评估以及在交互式实验环境中管理提示词生命周期提供了资源。

This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals. The framework emphasizes multi-agent system orchestration through distributed architectures where specialized agents collaborate using standardized communication protocols. It details specific design patterns such as dual-memory systems for maintaining short-term plans and

该项目是一个用于构建、评估和连接自主代理系统的综合框架。它提供了一个标准化架构模式库，用于实现复杂的代理工作流，包括多代理编排、迭代推理和内存管理。通过为模型提供者提供统一接口，该框架允许跨不同人工智能服务进行一致的代理执行。 该框架通过专注于严格的基准测试和确定性控制脱颖而出。它包括一套用于根据标准化任务和质量指标评估代理性能的工具，从而能够比较不同的设计模式。为了确保可靠性，该系统结合了确定性路由门和自校正循环，在外部执行前验证代理操作并根据质量标准优化输出。 该架构支持广泛的功能，包括用于现实世界任务完成的工具集成、用于上下文感知响应的检索增强生成，以及用于跨会话维护信息的模块化内存管理。这些组件通过标准化的执行契约链接，确保无论底层模型或特定架构配置如何，行为都保持一致。 该存储库结构化为一系列演示这些模式和基准测试方法的 Jupyter Notebooks。