22 个仓库
Systems that translate natural-language problem descriptions into executable source code for automated evaluation.
Distinct from Specification from Code Generators: Distinct from Specification from Code Generators: generates executable code from natural language, not API specs from annotated code.
Explore 22 awesome GitHub repositories matching programming languages & runtimes · Natural Language Code Generators. Refine with filters or upvote what's useful.
Qwen2.5-Coder is a code-centric large language model designed to generate, complete, and analyze source code. It serves as a polyglot programming model capable of producing functional code across hundreds of different programming languages. The model is optimized for reasoning over extensive software repositories, utilizing a context window that supports up to one million tokens. It also functions as an agentic coding framework, executing multi-step workflows and browser tasks through specialized function call formats. Its capabilities include large-scale codebase analysis, intelligent parti
Generates functional source code in hundreds of programming languages from natural language descriptions.
Code Llama is a large language model based on Llama 2 trained specifically for programming tasks and software development. It provides specialized model types optimized for general code generation, instruction following, and context-aware infilling. The project includes an instruction-tuned programming model for executing technical tasks via natural language prompts and a code infilling model that predicts missing sections based on surrounding source context. A large context code model is also provided to analyze extensive blocks of source code for improved coherence. The system covers capab
Translates natural-language problem descriptions and technical instructions into executable source code.
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
Transforms natural language requirements into executable source files and directory structures.
Gop 是一种通用编程语言和跨语言编译器,旨在将来自多个编程生态系统的资产和库统一到一个共享环境中。它使用针对不同目标环境定制的专用后端,将高级源代码转换为可执行二进制文件。 该项目具有自然语言编程系统,可将用纯英语编写的人类可读指令转换为可执行代码。它还充当跨语言工具,在编译过程中导入并集成来自不同语言生态系统的外部库和资产。 其功能面包括一个将文件名映射到 API 端点的基于文件的 Web 框架、一个用于数据提取的基于 DOM 的 HTML 解析器,以及一个利用事件驱动对话系统的基于 Actor 的 2D 游戏引擎。此外,它还为执行 Shell 命令和用于 DevOps 任务自动化的管理脚本提供了简化的语法。
Transforms human-readable English instructions into executable source code through a specialized translation layer.
Evolver is a self-evolving AI agent framework that uses gene expression programming to autonomously improve agent behaviors through a continuous five-step loop of scanning, selecting, mutating, validating, and solidifying. It functions as an auditable evolution system that records every mutation and selection step, and can translate natural-language problems into executable Python code for automated grading and evaluation. The framework distinguishes itself through a distributed architecture that enables multiple agents to collaborate and share learned experiences across a network. It operate
Translates natural-language problems into executable Python code with automated grading and error repair.
curlconverter is a browser-based tool and JavaScript library that transforms curl commands into equivalent source code across more than 30 programming languages and HTTP client libraries. It parses curl command arguments into an abstract syntax tree and generates idiomatic code by applying per-language templates, making it a curl command transpiler rather than a simple converter. The tool operates entirely client-side without any server round-trips, ensuring all conversion happens privately in the browser without transmitting data externally. It can also function as a drop-in curl replacement
Applies per-language templates to translate parsed curl options into idiomatic HTTP client code.
TrumpScript is a Python-based domain specific language and compiler extension that wraps the Python runtime to enforce custom grammar and vocabulary rules. It transforms a specialized, case-insensitive vocabulary and natural speech patterns into executable Python instructions. The implementation distinguishes itself through strict constraints on source code, including a variable name system that restricts identifiers to a predefined whitelist and a numeric parser that rejects any integer not exceeding one million. It further utilizes a token-filtering preprocessor to remove filler words and n
Discards unnecessary words from the source code to make it resemble natural human speech.
CodeGeeX2 is a large language model and AI programming assistant designed to generate, translate, and document source code across multiple programming languages. It functions as a multilingual code model that converts natural language prompts into executable code and technical documentation. The project provides a self-hosted AI inference endpoint, allowing the model to be exposed as a web-accessible service. This enables external development tools to integrate automated programming tasks via network calls. Its core capabilities cover multilingual code generation, automated source code docum
Translates natural-language prompts into executable source code and completes existing code snippets.
sqlboiler is a database-first ORM generator for Go that analyzes an existing database schema to produce strongly typed structures and query helpers. It functions as a schema-driven code generator, transforming database tables and relationships into executable Go source code. The project distinguishes itself through a type-safe query builder that uses chainable modifiers to construct SQL statements, eliminating the need for raw string concatenation. It utilizes customizable text templates to generate source code, allowing for the aliasing of schema entities and the creation of custom templates
Uses customizable text templates to transform database metadata into executable Go source code.
Llamacoder is an AI-powered web application generator that transforms natural language prompts into functional application prototypes. It uses large language models to synthesize code and layouts, enabling the creation of small-scale software and interactive user interfaces from text descriptions. The project specifically leverages the Llama 3.1 405B model to produce executable React components. It provides a self-hosted environment for generating and previewing interactive code artifacts, featuring a real-time preview loop and sandboxed component rendering to safely display generated interfa
Translates natural-language prompts into executable frontend source code using a large language model.
DevOpsGPT 是一个由大语言模型驱动的 DevOps 自动化平台和 AI 软件开发代理。它通过协调代码库分析、代码生成和交付流水线,将自然语言需求转换为功能代码和自动化部署。 该系统具有自动化代码生成引擎和基于任务的分解引擎,可分析项目结构以生成上下文感知的代码扩展。它利用可插拔的模型集成系统连接到私有或专业语言模型部署,以执行特定领域的开发任务。 该平台通过 CI/CD 流水线编排器管理完整的软件交付生命周期,该编排器将代码合成与自动化测试和部署工具链接起来。这包括软件版本发布以及与各种外部 DevOps 平台集成的功能。
Translates natural-language problem descriptions into executable source code for automated evaluation.
Hygen is a code generator CLI and interactive template engine that scaffolds new files and injects code into existing ones using project-local templates. It operates as a Node.js code generator library that can be embedded inside custom binaries for tailored workflows, and also functions as a project scaffolding tool for bootstrapping new projects or folders from remote template repositories. The tool discovers templates by scanning a project's _templates directory at runtime, mapping folder and file names directly to generator commands and actions. It collects user input through interactiv
Scaffolding new files and injecting code into existing ones using project-local templates and a fast command-line interface.
This project provides methodologies and guides for structured prompt engineering, generative workflows, and specialized image generation strategies. It serves as a framework for optimizing inputs to large language models across coding, writing, and analysis tasks, as well as a library of techniques for controlling diffusion models. The project distinguishes itself through an AI-driven software design framework that converts business requirements into technical architectures and code using domain-driven prompting. It also implements generative AI workflow patterns that use sequential prompt pi
Defines formal syntax rules using natural language prompts to automate the creation of domain-specific languages.
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。
Translates natural language prompts and visual data into executable Python scripts for visual analysis.
CodeGen 是一个经过训练的大语言模型与程序合成模型,旨在生成功能性源代码。它利用神经网络架构,根据自然语言描述或部分代码片段合成可执行代码。 该模型通过预测并填充程序中缺失的代码部分,实现了自动化程序合成与 AI 辅助编码。它将自然语言描述转换为功能性编程逻辑,以自动化样板代码与业务逻辑的创建。
Performs automated program synthesis to generate complete functional code from natural language prompts.
Integuru 是一个由 AI 驱动的代理和框架系统,旨在记录未文档化的 API 并将网络流量转换为自动化脚本。它作为一个无头 API 自动化框架,用直接的 HTTP 请求取代基于浏览器的工具,以提高吞吐量和可靠性。 该项目具有一个基于 LLM 的逆向工程代理,用于分析网络流量以发现内部 API;以及一个自然语言集成引擎,将工作流的文本描述转换为有效的 API 调用序列。它包括用于提取请求和响应格式以创建精确技术规范的工具,以及将捕获的会话 Cookie 转换为生产级自动化脚本的工具。 该框架涵盖了广泛的功能,包括模式工程、请求依赖图谱和基于状态的逻辑映射,以处理复杂的应用工作流。它还为会话 Cookie 提供自动身份验证管理和多因素验证,以保持对受保护门户的访问。
Converting plain text descriptions of desired actions into production-ready HTTP requests and automation scripts.
Briefer is an interactive data notebook platform and business intelligence dashboard tool used for collaborative data analysis and reporting. It provides a containerized environment for building reports that combine SQL, Python, and Markdown with native visualizations. The platform features an integrated code assistant that uses large language models to generate SQL and Python snippets from natural language prompts. It is designed as a Kubernetes data application, deploying via Helm charts to manage isolated compute environments and ensure separate resources per page through pod-based isolati
Includes an integrated code assistant that generates SQL and Python snippets from natural language prompts.
该项目是 JupyterLab 的一个扩展,将大语言模型提供商和 AI 代理直接集成到计算笔记本中。它作为一个集成层和编排器,连接生成式 AI 后端与数据科学工作区,从而实现在笔记本单元格中执行 AI 提示词并将生成的代码块插入文档。 该系统具有一个协作聊天界面,多个用户可以实时与 AI 人格互动,共享对话线程并利用拖放文件附件来提供上下文。它允许创建自定义 AI 人格并通过协议服务器集成专用工具,同时保持与提供商无关的接口以切换不同的大语言模型后端。 功能包括自动化工作流,如文件管理、代码调试和 shell 命令执行。为确保安全,该框架采用权限门控执行,要求在 AI 代理修改文件或运行系统命令之前获得明确的用户批准。
Allows transferring AI-generated code blocks directly from the chat interface into the notebook as new or replacement cells.
Cheetah 是一个由原生 macOS 应用程序和浏览器扩展组成的 LLM 技术面试助手。它通过结合实时音频转录和基于 Web 的上下文提取,在技术面试期间提供实时编码和回答建议。 该系统作为一个实时面试教练,使用设备端语音转录技术将口头问题转换为文本。它使用浏览器集成的 DOM 抓取器提取实时代码和控制台日志,允许 AI 分析当前的编码状态并根据面试的具体环境生成技术解决方案。 该工具支持迭代响应优化,允许用户在面试官提供新的约束或澄清时更新建议的答案。这些功能涵盖了技术面试准备和实时 AI 编码辅助的更广泛领域。
Analyzes the current state of live code and logs to provide real-time technical assistance.
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。
Builds prototypes and features through an iterative natural language dialogue.