LangGraph
Multi-agent orchestration framework with state graphs
Overall score
About
LangGraph is a low-level orchestration framework from LangChain for building stateful, multi-agent workflows as directed graphs. It pairs with LangGraph Platform for managed deployment, persistence, and human-in-the-loop controls.
Best for: Engineering teams building production multi-agent systems that need fine-grained control over state, branching, and persistence.
Pricing
Self-hosted (OSS)
- Monthly
- n/a
- Annual /mo
- Free
- Billing
- flat
- Notes
- Full open-source framework;Self-managed deployment · MIT licensed core
Developer
- Monthly
- n/a
- Annual /mo
- Free
- Billing
- usage_based
- Notes
- Up to 100K nodes/mo;1 dev deployment · Free tier on LangGraph Platform
Plus
- Monthly
- $39
- Annual /mo
- $39
- Billing
- usage_based
- Notes
- Production deployments;Higher node limits;Standard support · Plus seats plus usage
Enterprise
- Monthly
- n/a
- Annual /mo
- n/a
- Billing
- seat_based
- Notes
- Self-hosted control plane;SSO;SOC 2;Dedicated support · Contact sales
| Tier | Monthly | Annual /mo | Billing | Notes |
|---|---|---|---|---|
| Self-hosted (OSS) | n/a | Free | flat | Full open-source framework;Self-managed deployment · MIT licensed core |
| Developer | n/a | Free | usage_based | Up to 100K nodes/mo;1 dev deployment · Free tier on LangGraph Platform |
| Plus | $39 | $39 | usage_based | Production deployments;Higher node limits;Standard support · Plus seats plus usage |
| Enterprise | n/a | n/a | seat_based | Self-hosted control plane;SSO;SOC 2;Dedicated support · Contact sales |
Key features
- Graph-based agent workflows
- Built-in persistence
- Streaming and time-travel
- Human-in-the-loop checkpoints
- Managed Platform deploys
- Observability via LangSmith
Integrations
Trust & compliance
- Stage range
- Seed → Growth
- Founded
- 2022
- Status
- active
- SOC 2
- yes
- GDPR
- yes
- Data residency
- us
- External rating
- 4.6 on GitHub (12000 reviews)
- Last verified
- Jun 2026
Reviews
Be the first to share your experience.
Related tools in Agents
Pairs well with
People who've discussed LangGraph
See all people →Curated mentions from podcasts, posts, and public stacks. Editorial coverage; not endorsements.
Andrew Ng
Founder; AI Educator
Andrew Ng launched a course on LangGraph for building single and multi-agent LLM applications, taught directly by LangChain founder Harrison Chase. The course covers integrating agentic workflows using LangGraph as the orchestration substrate. Part of Ng's broader agentic-AI curriculum that frames LangGraph as the canonical state-graph framework for multi-agent systems.
Harrison Chase
Co-founder & CEO
LangGraph is the LangChain team's stateful agent framework, presented as 'a LangChain extension that makes it really easy to define agents as graphs'. Chase frames LangGraph as the best way to build agents because of three properties: controllability, memory, and novel UX paradigms. He partnered with DeepLearning.AI on a dedicated AI Agents in LangGraph course.