Awesome GitHub RepositoriesCode Modification Systems

Autoresearch is an autonomous machine learning research agent and architecture search framework. It employs a closed-loop system to programmatically rewrite training and architecture source code to discover optimal language model configurations. The system iteratively modifies code and evaluates performance metrics to improve model quality based on a target objective. It optimizes model performance and training efficiency by tracking validation bits per byte, which allows for a fair comparison of architectural changes independently of vocabulary size. The framework manages the full training

Oh-my-opencode is an autonomous software engineering platform designed to automate complex coding tasks through the orchestration of specialized AI agents. It manages end-to-end development workflows by coordinating teams of agents that perform parallel execution, strategic planning, and automated code generation. The system ensures high-precision refactoring by utilizing a hash-anchored modification engine, which verifies file integrity through cryptographic line references before applying any changes. The platform distinguishes itself through a rigorous planning-first methodology, requiring

Strix is an automated security research and vulnerability scanning platform that leverages language models to orchestrate complex security analysis tasks. It functions as a comprehensive framework for penetration testing and continuous security integration, allowing users to embed automated vulnerability research directly into development pipelines or execute it within isolated, containerized environments. The platform distinguishes itself through a multi-agent orchestration engine that coordinates specialized autonomous agents to perform parallel security assessments. By integrating LLM-agno

Helium is a browser engine compilation framework designed to automate the creation of custom web browser binaries from Chromium source code. It functions as a build system that manages the complex dependency toolchains and environment configurations necessary to transform raw source code into functional, cross-platform software applications. The project distinguishes itself through a structured patch-series management system, which allows developers to maintain and apply custom modifications to large-scale codebases across frequent upstream updates. This workflow ensures that specialized feat

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

tModLoader is a modding framework and toolset designed for expanding game content and extending core game logic. It provides a polymorphic content API that allows for the creation of new items, NPCs, projectiles, and world assets through object-oriented inheritance. The project is distinguished by its advanced code modification capabilities, utilizing intermediate language bytecode patching and reflection-based private access to alter internal game behavior. It features a hot-reloading assembly runtime that enables developers to recompile and apply source code changes in real-time without res

Cet outil fonctionne comme un serveur de protocole de contexte de modèle (Model Context Protocol) qui relie les modèles d'intelligence artificielle aux environnements de développement locaux. Il permet aux assistants IA d'effectuer une analyse de base de code, d'exécuter des utilitaires en ligne de commande et d'appliquer des modifications de code automatisées directement sur les fichiers de projet locaux. En s'intégrant à l'API Gemini, le système facilite une interaction profonde entre les modèles externes et les ressources système locales. Le projet se distingue par un cadre de sécurité et de fiabilité robuste conçu pour les flux de travail de développement automatisés. Il applique des contrôles d'accès stricts basés sur les chemins pour protéger les fichiers sensibles et utilise des environnements sandbox isolés pour exécuter le code généré. Pour assurer une opération continue, l'outil implémente un routage de secours dynamique des modèles, qui bascule automatiquement entre les niveaux de modèle si les limites d'utilisation sont atteintes, et utilise un jugement de modèle secondaire pour valider la qualité des sorties générées. Le système prend en charge un large éventail d'opérations techniques, y compris l'extraction de données structurées à partir de la sortie du terminal, la gestion de l'historique des conversations et la configuration des paramètres d'exécution pour les tâches de longue durée. Il fournit des capacités complètes pour scanner les répertoires de projet, générer des informations techniques et gérer les fenêtres de contexte pour traiter une documentation et des informations de base de code étendues.