3 个仓库
Systems that automatically generate source code and modify project files by following a predefined implementation plan.
Distinct from Implementation Planning: Distinct from Implementation Planning: focuses on the automatic code generation step after planning, not the planning workflow itself.
Explore 3 awesome GitHub repositories matching software engineering & architecture · Plan-Driven Code Generators. Refine with filters or upvote what's useful.
Vision-agent 是一个 AI 系统和视觉数据提取框架,可将自然语言提示转换为可运行的 Python 脚本,用于分析图像和视频。它作为一个多模型视觉编排器,利用大语言模型来规划并生成用于目标检测、计数和视频跟踪等任务的可执行代码。 该系统采用“规划-执行”循环,迭代生成并测试代码,利用纠错循环来优化实现,直到解决方案通过验证。它是配置驱动的,允许通过环境变量和配置文件路由底层的语言模型后端。 除了自动化代码生成外,该框架还集成了专门的计算机视觉工具,以执行视觉对象分析并从媒体中提取结构化数据。这允许视觉功能独立执行,或作为更大自动化工作流的一部分执行。
Automatically generates and iterates upon runnable Python code based on a predefined implementation plan.
Costrict 是一款专为企业级开发设计的 AI 软件工程代理和编码助手。它作为一个多模型 AI 编排器,负责生成、补全和审查代码,同时作为一个远程开发环境,连接浏览器界面与远程目录以进行文件管理和终端执行。 该平台的独特之处在于其 AI 代码审查系统,该系统利用多模型验证和仓库索引来确保代码质量。它采用结构化代理方法,将复杂的自然语言需求分解为有序的分析、规划和测试工作流,以保持架构控制。 该系统涵盖了广泛的功能领域,包括远程工作空间管理、自定义 AI 模型集成,以及针对仓库和 git diff 的自动化代码审查。它还通过基于技能的代理系统提供了可扩展性,并通过标准化上下文协议与外部工具集成。 该项目使用 TypeScript 实现,并提供基于插件的编辑器集成,以标准化受支持代码编辑器内的工作流。
Decomposes complex requirements into sequenced analysis, planning, and testing steps for predictable code generation.
Conductor is an agentic coding tool that plans, generates, and manages software features through structured tracks and human-reviewed plans. It operates as a plan-driven code generator, reading structured plan files to determine the sequence of tasks and their dependencies before executing any code generation or modification. The system also functions as a feature specification manager, defining features in formal specification files that capture goals, requirements, and implementation steps as machine-readable documents. The tool distinguishes itself through a git-history-based undo system t
Generates source code and modifies project files automatically by following a predefined implementation plan.