4 个仓库
Loads isolated tools and skills dynamically at runtime to extend AI agent capabilities without modifying core code.
Distinct from Plugin Extenders: Distinct from Plugin Extenders: specifically targets AI agent skill and tool extension rather than general application plugin loading.
Explore 4 awesome GitHub repositories matching software engineering & architecture · Agent Skill Extenders. Refine with filters or upvote what's useful.
Edict is a multi-agent orchestration system and framework designed to coordinate specialized large language model agents. It functions as a workflow designer and orchestrator that decomposes complex objectives into structured plans, using directed acyclic graphs and role-based hierarchies to execute sub-tasks. The system is distinguished by its event-driven architecture, utilizing a publish-subscribe event bus and transactional outbox to manage agent communications and task transitions. It features a dedicated skill management system that allows for the importation, updating, and sandboxed ex
Loads isolated tools and specialized skills dynamically at runtime via URLs or file paths.
IntentKit is an open-source platform for deploying and managing a collaborative team of AI agents that can work together to complete complex tasks. It provides a self-hosted agent orchestrator that coordinates multiple agents through a modular pipeline of entrypoints, orchestration, and storage, all running as containerized services using Docker Compose or Swarm for production-grade deployment. The platform distinguishes itself by offering a plugin-based system for extending agent capabilities without modifying the core codebase, along with built-in integrations for connecting agents to socia
Extends agent capabilities through a pluggable skill system without modifying the core codebase.
Material Kit is an open-source UI component library that provides pre-styled Material Design elements for building responsive web interfaces with Bootstrap 5. It offers a collection of reusable components like buttons, inputs, navbars, cards, and modals that follow Google's Material Design guidelines, along with a 12-column flexbox grid system for fluid layouts that adapt to any screen size. The kit distinguishes itself by including pre-built page sections such as headers, feature blocks, pricing tables, and footers that can be combined into complete page layouts, reducing the time needed to
Mentions installing pre-built skills for AI agents, but this is not a capability of the repository.
本项目是一个多渠道 AI 代理和聊天机器人框架,允许将单一 AI 智能部署到各种消息平台、Web 界面和电子邮件账户中。它作为一个跨模型 AI 网关,提供统一的接口来路由不同大语言模型提供商之间的请求。 该系统以其自主任务规划和知识管理能力而著称。它可以使用外部工具和无头浏览器将复杂目标分解为顺序执行步骤,同时从对话中提取信息以构建带有可视化关系图的结构化知识库。 该平台包含用于长期上下文检索的分层记忆系统、用于扩展功能的动态技能插件引擎,以及执行远程系统命令的能力。它还支持多模态工作流,能够在不同通信渠道之间交换图像、语音消息和文件。 该实例可以通过 Web 控制台、基于终端的命令行界面或聊天中的斜杠命令进行管理。
Features a dynamic engine that loads isolated tools and skills at runtime to extend agent capabilities.