2 个仓库
Mechanisms for defining and registering executable tools that allow AI models to interact with external systems or perform specific tasks.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Agent Tool Registries. Refine with filters or upvote what's useful.
Openclaw 是一个用于管理智能体(Agent)执行环境的平台,提供控制智能体生命周期、会话状态和工作区持久化的基础设施。它具有一个处理模型循环、工具调用和流式事件的中心化网关,同时支持多智能体路由和持久化内存管理。该系统旨在规范工具执行签名,并为跨提供商兼容性提供标准化接口。 该平台包括广泛的开发者工具,例如用于工作区管理的命令行界面、诊断日志记录以及允许注册自定义工具和功能的插件架构。它通过事件驱动的钩子、任务调度和与外部服务的集成来支持自动化工作流。安全性通过执行策略、凭据可移植性和智能体操作的审批工作流进行管理。 部署通过自动化基础设施安装程序和容器化网关助手提供支持,并内置了用于备份和配置管理的实用程序。该系统为编排多步工作流提供了结构化格式,并包括用于浏览器自动化和结构化代码补丁的专用工具。
Registers executable tools for model access while enforcing strict allowlisting and validation protocols.
LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public
A mechanism for converting standard functions into discoverable tools that language models can invoke via reasoning.