Skip to content
masterclass Buddy
Start learning

LangChain · Class

AgentExecutor

AgentExecutor runs an agent with a sequence of tools. Create it with from_agent_and_tools, then invoke it with input data.

Last updated

Since
v1.4

Syntax

AgentExecutor.from_agent_and_tools(cls, agent: BaseSingleActionAgent | BaseMultiActionAgent | Runnable, tools: Sequence[BaseTool], callbacks: Callbacks = None, kwargs: Any = {}) -> AgentExecutor

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • AgentExecutorIterator
  • BaseSingleActionAgent
  • BaseMultiActionAgent
  • BaseTool
  • Chain

Source: from_agent_and_tools | langchain_classic | LangChain Reference. Checked 2026-11-03.