5 dépôts
Configuration-driven systems that manage the installation, lifecycle, and activation of plugins for agent frameworks.
Explore 5 awesome GitHub repositories matching artificial intelligence & ml · Plugin Management Systems. Refine with filters or upvote what's useful.
Openclaw est une plateforme de gestion d'environnements d'exécution d'agents, fournissant l'infrastructure nécessaire pour contrôler les cycles de vie des agents, l'état des sessions et la persistance des espaces de travail. Elle dispose d'une passerelle centralisée qui gère les boucles de modèles, l'invocation d'outils et les événements en streaming, tout en prenant en charge le routage multi-agents et la gestion de la mémoire persistante. Le système est conçu pour normaliser les signatures d'exécution des outils et fournir une interface standardisée pour la compatibilité entre les fournisseurs. La plateforme inclut des outils de développement étendus, tels qu'une interface en ligne de commande pour la gestion des espaces de travail, la journalisation de diagnostic et une architecture de plugins qui permet l'enregistrement d'outils et de capacités personnalisés. Elle prend en charge les flux de travail automatisés via des hooks pilotés par les événements, la planification des tâches et l'intégration avec des services externes. La sécurité est gérée par des politiques d'exécution, la portabilité des identifiants et des flux de travail d'approbation pour les actions des agents. Le déploiement est pris en charge par des installateurs d'infrastructure automatisés et des assistants de passerelle conteneurisés, avec des utilitaires intégrés pour les sauvegardes et la gestion de la configuration. Le système fournit un format structuré pour orchestrer des flux de travail en plusieurs étapes et inclut des outils spécialisés pour l'automatisation des navigateurs et le patch de code structuré.
Configures the automatic installation and activation of plugins prior to agent execution.
OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It
Control the installation and activation status of plugins through persistent storage management.
This project is a command line AI client and API wrapper designed to facilitate interaction with a large language model. It functions as a terminal interface for sending multi-line prompts and receiving generated text, providing a means of conversational AI integration through a programmable interface. The system utilizes a reverse-engineered API interface and HTTP-based request simulation to communicate with the model. It includes an AI plugin manager that allows for the installation and management of external extensions to increase the functional capabilities of the language model. The imp
Implements a plugin management system for extending the capabilities of the integrated language model.
LangBot is an orchestration platform designed for building, managing, and deploying AI agents. It functions as a comprehensive framework for integrating large language models with custom workflows, enabling developers to connect intelligent agents to various messaging platforms and external tools. The platform distinguishes itself through a modular, plugin-based architecture that allows for the extension of agent capabilities via custom tools and file parsers. It features a secure, sandbox-isolated runtime environment that executes untrusted code and plugin logic within resource-constrained c
Dify initializes plugins, manages individual components, and interacts with external marketplaces to facilitate bot development.
This project is a plugin framework for extending autonomous LLM agents. It enables the integration of external scripts and third-party services into an agent's workflow without modifying the core code. The framework utilizes an event-driven hook system to execute plugin functions at predefined stages of an agent's lifecycle. It includes a sandboxed code executor to run external extensions in a secure, isolated environment. The system manages the lifecycle of external modules through a dependency injection manager and supports loading extensions from local directories or zipped archives. Conf
Provides a configuration-driven system to manage the installation, lifecycle, and activation of agent plugins.