12 dépôts
Strategies for building features in small, verifiable vertical slices using test-driven development.
Distinct from Incremental Build Engines: Candidates focus on build-system performance (compilation), whereas this is about the software development methodology of incremental feature delivery.
Explore 12 awesome GitHub repositories matching software engineering & architecture · Incremental Implementations. Refine with filters or upvote what's useful.
Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated
Provides a framework for implementing features via thin vertical slices and continuous verification.
Devika is an autonomous AI software engineering system designed to plan, write, and debug code from high-level natural language instructions. It functions as an agentic software engineer that decomposes complex objectives into actionable coding steps for autonomous execution. The system integrates cloud-based and self-hosted large language models through a provider-agnostic layer, allowing for multi-model reasoning and code completion. It distinguishes itself by combining these models with a sandboxed execution environment for running code across different operating systems and a web-browsing
Modifies project files to add new capabilities while maintaining existing code style and performing incremental verification.
This project is a Lisp interpreter implementation guide and framework designed to teach the core principles of programming language design. It provides a structured, step-by-step technical framework for building a functional Lisp language from scratch, featuring a specialized interpreter engine and an S-expression parser that converts syntax into abstract syntax trees. The project emphasizes a code-as-data metaprogramming framework, enabling the implementation of macros, quoting, and quasiquoting to transform expressions during evaluation. It is designed with host language agnosticism, allowi
Organizes the interpreter build process into a sequence of verifiable, incremental implementation stages.
vibe-coding-cn is an AI software development workflow and prompt engineering framework designed to transform product ideas into functional applications using natural language. It functions as an AI agent orchestration system that coordinates specialized skills and quality gates to guide the incremental creation of software. The framework distinguishes itself through a project memory system that maintains architectural and design documentation to preserve context during long-term collaborations. It employs a prompt optimization library that utilizes recursive loops, chain-of-thought reasoning,
Builds complex features using small-step instructions and mandatory verification tests to ensure successful delivery.
Sweep est un système d'ingénierie logicielle automatisé qui utilise des grands modèles de langage (LLM) pour résoudre les issues GitHub. Il fonctionne comme un ingénieur logiciel IA qui transforme les descriptions d'issues en langage naturel en modifications de code concrètes et en pull requests. Le système s'intègre aux webhooks GitHub pour déclencher des workflows basés sur la création d'issues ou les mises à jour de labels. Il utilise une boucle de rétroaction itérative qui analyse les erreurs de compilation et les résultats de tests pour affiner le code généré et corriger les bugs. L'outil couvre une gamme de capacités de maintenance, incluant la correction automatique de bugs, l'implémentation de fonctionnalités et le refactoring de codebase. Il intègre l'analyse statique et le prompting contextuel pour garantir que le code généré respecte les standards de typage, de logging et d'architecture spécifiques au projet. La sécurité est gérée par des garde-fous basés sur des règles et des restrictions d'accès qui empêchent l'agent de modifier des fichiers ou des répertoires protégés.
Automatically implements new requested features from GitHub issues while preserving existing codebase styles.
This is an open-source educational website that translates and localizes MIT's Missing Semester course, teaching practical computing skills for computer science students. The curriculum covers developer tooling, shell scripting, version control, security fundamentals, and open-source collaboration, with a focus on core computing skills including data processing pipelines, workflow automation, secure remote access, shell productivity, Vim editing, and Git version control. The project distinguishes itself by teaching command-line mastery, shell scripting, and automation to boost daily developer
Teaches translating a descriptive specification into working code with iterative refinement.
This project is a reference catalogue of the new syntax and behavioral changes introduced in the ECMAScript 6 (ES6) specification for JavaScript. It serves as a curated overview and comparison table of the language features defined by the standard, documenting additions such as block scoping with let and const, arrow function syntax, default parameter handling, and rest parameter collection. The reference is structured as a side-by-side comparison chart that maps old and new JavaScript syntax patterns, providing a focused guide for each capability. It covers the core language fundamentals
Organises ES6 features by their specification section for side-by-side comparison.
DevOpsGPT est une plateforme d'automatisation DevOps pilotée par LLM et un agent de développement logiciel IA. Il transforme les exigences en langage naturel en code fonctionnel et en déploiements automatisés en coordonnant l'analyse de la base de code, la génération de code et les pipelines de livraison. Le système dispose d'un moteur de génération de code automatisé et d'un moteur de décomposition basé sur les tâches qui analysent les structures de projet pour produire des extensions de code sensibles au contexte. Il utilise un système d'intégration de modèles enfichables pour se connecter à des déploiements de modèles de langage privés ou professionnels pour des tâches de développement spécifiques au domaine. La plateforme gère l'intégralité du cycle de vie de livraison logicielle via un orchestrateur de pipeline CI/CD qui lie la synthèse de code aux outils de test et de déploiement automatisés. Cela inclut des capacités pour la publication de versions logicielles et l'intégration avec diverses plateformes DevOps externes.
Autonomously modifies project files to add new capabilities while preserving existing code styles.
Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases. The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for
Generates detailed implementation plans and surfaces clarifying questions to define new feature specifications.
Agent-OS is an LLM multi-agent orchestration framework and AI software development lifecycle tool designed to coordinate specialized agents through shared workspaces and structured task lists. It functions as an agentic application bootstrapper and technical specification engine, providing the infrastructure to guide the process from product requirements to automated coding and deployment. The system distinguishes itself through spec-driven development, using detailed technical specifications and layered context injection to ensure generated code aligns with project standards. It employs a ma
Generates detailed functional requirements and sample data to guide the development of specific application screens.
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
Planning, specifying, and implementing software features through structured tracks with human review before code generation.
Ce projet est une ressource pédagogique conçue pour enseigner le développement logiciel bas niveau à travers la construction incrémentale d'un éditeur de texte fonctionnel en terminal. Il propose un cursus étape par étape qui guide les utilisateurs dans la création d'une application interactive en C, en utilisant la gestion standard des entrées du terminal. Le tutoriel se distingue par l'utilisation d'un modèle d'implémentation incrémental, où chaque étape fonctionnelle s'appuie sur le code précédent pour assurer une courbe d'apprentissage progressive. Pour soutenir ce processus, le projet inclut un utilitaire en ligne de commande qui compare le code source local aux implémentations de référence, normalisant les espaces et le formatage pour vérifier la justesse de chaque étape de développement. Le cursus couvre l'architecture fondamentale des terminaux, y compris la gestion des entrées en mode brut (raw mode), la gestion dynamique des buffers et l'utilisation de séquences d'échappement pour le rendu à l'écran. Ces exercices offrent une expérience pratique dans la gestion d'interfaces utilisateur en terminal et de structures de données textuelles. La documentation du projet est structurée pour faciliter l'apprentissage en autonomie et est prête pour un déploiement sur des environnements d'hébergement distants.
Structures the learning process into small, functional milestones that build incrementally upon previous code.