Namespace LMKit.Agents
Namespaces
Classes
- Agent
Represents an AI agent capable of executing tasks using a language model, tools, and reasoning strategies.
- AgentBuilder
Fluent builder for constructing Agent instances with a chainable API.
- AgentCapabilities
Encapsulates the capabilities available to an agent: tools, skills, and memory.
- AgentExecutionOptions
Configuration options for agent execution, providing fine-grained control over context sizing, iteration limits, timeouts, and output constraints.
- AgentExecutionResult
Represents the outcome of an agent task execution.
- AgentExecutor
Default executor for running agents using MultiTurnConversation.
The executor creates and manages a conversation context, applies the agent's configuration, handles the execution loop including tool calls and planning strategies, and produces execution results.
- AgentIdentity
Represents the identity of an agent, defining its persona and behavioral instructions.
- AgentMemory
Provides persistent memory storage and retrieval capabilities for conversational agents using retrieval-augmented generation (RAG).
- AgentRegistry
A collection that manages named agents for lookup and delegation scenarios.
Interfaces
- IAgentExecutor
Defines the contract for executing agent tasks.
An executor is responsible for running an agent against input prompts, managing the execution loop, handling tool calls, and producing results.
Enums
- AgentExecutionStatus
Represents the terminal status of an agent task execution.
- PlanningStrategy
Specifies the reasoning and planning approach an agent uses to decompose and solve tasks.