These docs are for the v1.0 alpha release of LangGraph. For the latest stable docs, please see the old sites: LangGraph Python | LangGraph JavaScript
What is an agent?
An agent consists of three components: a large language model (LLM), a set of tools it can use, and a prompt that provides instructions. The LLM operates in a loop. In each iteration, it selects a tool to invoke, provides input, receives the result (an observation), and uses that observation to inform the next action. The loop continues until a stopping condition is met — typically when the agent has gathered enough information to respond to the user.
Key features
LangGraph includes several capabilities essential for building robust, production-ready agentic systems:- Memory integration: Native support for short-term (session-based) and long-term (persistent across sessions) memory, enabling stateful behaviors in chatbots and assistants.
- Human-in-the-loop control: Execution can pause indefinitely to await human feedback—unlike websocket-based solutions limited to real-time interaction. This enables asynchronous approval, correction, or intervention at any point in the workflow.
- Streaming support: Real-time streaming of agent state, model tokens, tool outputs, or combined streams.
- Deployment tooling: Includes infrastructure-free deployment tools. LangGraph Platform supports testing, debugging, and deployment.
- Studio: A visual IDE for inspecting and debugging workflows.
- Supports multiple deployment options for production.
Package ecosystem
The high-level, prebuilt components are organized into several packages, each with a specific focus:Package | Description | Installation |
---|---|---|
langgraph-prebuilt (part of langgraph ) | Prebuilt components to create agents | pip install -U langgraph langchain |
langgraph-supervisor | Tools for building supervisor agents | pip install -U langgraph-supervisor |
langgraph-swarm | Tools for building a swarm multi-agent system | pip install -U langgraph-swarm |
langchain-mcp-adapters | Interfaces to MCP servers for tool and resource integration | pip install -U langchain-mcp-adapters |
langmem | Agent memory management: short-term and long-term | pip install -U langmem |
agentevals | Utilities to evaluate agent performance | pip install -U agentevals |