2 个仓库
Standardized definitions of tools including metadata and execution logic for LLM invocation.
Distinct from Standardized Tool Execution: Shortlist candidates focus on interceptors or local execution, not the definition of the tool interface itself.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Executable Tool Definitions. Refine with filters or upvote what's useful.
Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che
Creates tool interfaces with metadata and execution logic that enable models to perform specific tasks.
这是一个用于在 Go 中实现 Model Context Protocol 的软件开发工具包(SDK)和框架。它提供了一套标准化的系统,用于构建交换外部资源、专有数据和可执行工具的服务器与客户端,从而为大语言模型提供上下文。 该 SDK 包含一个 JSON-RPC 通信库和一个集成框架,用于向 AI 模型公开本地数据、提示词模板和类型化函数。它支持开发提供外部上下文的协议服务器,以及消费这些远程工具和资源的客户端。 该项目涵盖了连接生命周期管理和协议版本协商,以确保互操作性。它提供了通过标准输入/输出或 HTTP 进行消息交换的传输抽象,以及资源映射和会话管理功能。 安全和可观测性功能包括 OAuth 身份集成、服务器目录访问限制,以及用于流量检查和能力验证的工具。
Provides standardized definitions for executable tools, including metadata and logic for LLM invocation.