Crate lc_agents 

Agent system for building autonomous LLM applications.

Provides core abstractions and implementations for agents.

Core Concepts

• Agent: Responsible for planning, deciding what action to execute next.
• AgentExecutor: Responsible for execution loop (plan -> act -> observe).
• Tool: Callable tools that agents can invoke.

Execution Flow

Input question
    |
Agent.plan() -> AgentAction or AgentFinish
    |
If Action: execute tool -> get observation
    |
Add to intermediate_steps
    |
Loop until AgentFinish returned

Re-exports

pub use adaptive_rag::AdaptiveRAG;

pub use adaptive_rag::AdaptiveRAGError;

pub use adaptive_rag::AdaptiveRAGResult;

pub use adaptive_rag::RagDecision;

pub use base::AgentError;

pub use base::AgentExecutor;

pub use base::BaseAgent;

pub use builder::AgentBuilder;

pub use crag::CRAGError;

pub use crag::CRAGResult;

pub use crag::CorrectiveRAGAgent;

pub use deep_research::Citation;

pub use deep_research::DeepResearchAgent;

pub use deep_research::ResearchError;

pub use deep_research::ResearchReport;

pub use function_calling::FunctionCallingAgent;

pub use handoffs::HandoffManager;

pub use plan_execute::PlanExecuteAgent;

pub use plan_execute::PlanExecuteError;

pub use react::ReActAgent;

pub use streaming::StreamingFunctionCallingAgent;

pub use types::AgentAction;

pub use types::AgentFinish;

pub use types::AgentOutput;

pub use types::AgentStep;

pub use types::ToolInput;

Modules

adaptive_rag

Adaptive RAG implementation.

base

Agent base traits and executor implementation.

builder

AgentBuilder — 3 行代码创建 Agent

crag

Corrective RAG (CRAG) Agent.

deep_research

Deep Research Agent: multi-round research with sub-topic decomposition, parallel search, and comprehensive report synthesis with citations.

function_calling

handoffs

Handoffs 多 Agent 交接

plan_execute

Plan-Execute Agent:规划-执行-重规划

react

ReAct Agent 实现

streaming

Streaming Tool Calls - 流式工具调用

types

Agent related type definitions