framework

LangGraph

by LangChain, Inc.

LangGraph is an open-source framework by LangChain for building stateful, multi-actor LLM applications modeled as directed graphs, where nodes represent actions or LLM calls and edges represent transitions. Unlike DAG-based pipelines, it supports cyclic execution enabling loops, retries, and conditional branching — the core primitives needed for reliable agentic systems. It ships with built-in state persistence, human-in-the-loop checkpointing, multi-agent coordination primitives, and deep LangSmith observability integration, and is backed by a managed deployment platform (LangGraph Platform).

8 Overall Score

Scores

Capability
9
Ease of Use
6
Documentation
8
Reliability
8
Value
9
Momentum
9

Details

Status
active
Pricing
open-source
Launch Date
2024-01
Last Updated
2026-03-15

Key Features

  • Cyclic graph execution — supports loops, retries, and conditional branching beyond simple DAGs
  • Persistent state & checkpointing — durable state across steps and sessions with pluggable backends
  • Human-in-the-loop — pause, await approval/input, then resume execution mid-graph
  • First-class multi-agent primitives — supervisor agents, subgraphs, and agent handoff patterns
  • LangSmith native observability — automatic tracing of every node, token usage, and latency
  • LangGraph Platform — managed cloud deployment with REST APIs, cron scheduling, and horizontal scaling

Tech Stack

PythonTypeScriptLangChain CorePydanticasyncioPostgreSQL (checkpointer backends)