LangGraph

 »  AI Agents  »  Framework  »  LangGraph  URL Share on

 Repository   27,370  4,706
Build resilient language agents as stateful graphs with cycles, branching, and persistence
multi-agent stateful-graphs durable-execution human-in-the-loop orchestration
TypeFramework
HostingHybrid
MaturityStable
Status Maintained

Key Features

Multi-Agent Single Agent Human-in-the-Loop Streaming Async Support Short-Term Memory Long-Term Memory Shared Memory Plugin System Custom Tools MCP Protocol A2A Protocol DAG Workflows CLI Self-Hosted Cloud Hosted

Community Feedback

  Strengths

  • Controllable multi-agent flows
  • Durable execution surviving failures
  • Human-in-the-loop support
  • Graph-based fine-grained control

  Weaknesses

  • Requires understanding graph concepts
  • Tightly coupled to LangChain ecosystem
  • Newer project with evolving API

LangGraph Details

OrganizationLangChain Inc
Organization TypeCompany
FundingSeries b+
CategoryFramework
SubcategoryOrchestration
DeploymentHybrid
Primary LanguagePython
RuntimePython 3.9+
LicenseMIT
Commercial UseUnrestricted
Install Commandpip install langgraph
GitHub Stars27,370
GitHub Forks4,706
Release CadenceWeekly
MaturityStable
Pricing ModelOpen core
Free TierMIT-licensed core is free
Self-Hosted FreeYes
Cost Modelfree + LLM costs
Community SizeLarge
Community ActivityVery active
Sentiment Positive
GPU RequiredNo
Research Date2026-03-24
LLM ProvidersAll via LangChain
API Keys RequiredLLM provider API key

Use Cases

When to Use

Best for: Complex multi-agent workflows needing durable execution and fine-grained control

Avoid when: Simple single-agent use cases or when LangChain dependency is unwanted

  Back to Agent Directory
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a