LangGraph
Open-source, MIT-licensed framework for building stateful, multi-agent AI workflows on cyclical graphs.
- Category
- Agent frameworks
- From
- $0/seat/month
- Pricing model
- freemium
- Free tier
- Yes
- Deployment
- Both
- Interface
- Library
- Open source
- Yes
- Public API
- Yes
- Model / LLM
- OpenAI, Anthropic, Google, AWS B…
Facts re-verified
On this page
Our verdict
LangGraph earns its place in the agent-framework category because its open-source core is genuinely free and it is the only mainstream framework built around cyclical, loopable graphs rather than one-way DAGs.
Production deployment on LangSmith is metered in two explicit units, LCUs and LSUs, on top of seat fees, so a small production setup can run from tens of dollars a month into the low hundreds before LLM costs. It is code-first, not a visual builder, and LangSmith's no-code offering is a separate product called Fleet. Pick it when you need fine-grained control of state, branching, interrupts and replay. Reach for CrewAI, Mastra or a simpler framework when you do not.
What is LangGraph?
LangGraph is an open-source, MIT-licensed Python and JavaScript library for building stateful AI agents as cyclical graphs of nodes and edges. It is built and maintained by LangChain and is the same engine underneath LangChain's own quick-start create_agent harness. For production work, LangGraph pairs with LangSmith, which adds tracing, evaluation, deployment and a no-code builder called Fleet, on top of the open-source core.
What does LangGraph do?
LangGraph lets developers define an agent as a graph whose nodes call models, tools or sub-agents, and whose edges define control flow. The graph is cyclical, so an agent can loop, retry and revisit earlier steps instead of only running as a one-way chain.
State is checkpointed after every node transition and can be persisted to Postgres, SQLite or Redis, which means a run survives a process restart and can be replayed from any prior checkpoint for debugging. A graph can also pause mid-run with a human-in-the-loop interrupt so a person can inspect or edit its state before it continues.
Cross-thread memory is exposed as a separate store layer for facts that need to persist across conversations. LangChain's create_agent is a higher-level harness that runs on top of LangGraph and composes a model, tools, prompt and middleware. It works with OpenAI, Anthropic, Google and other providers through a standard interface.
For production, LangGraph pairs with LangSmith, which adds tracing, evaluation, deployment, an LLM Gateway, an Engine for running agents, Sandboxes for code execution, and a no-code agent builder called Fleet.
The LangSmith trusted-by strip on 2026-08-23 lists Klarna, Vanta, Rippling, Lyft, Clay, Gong, Harvey, Autodesk, Workday, Cisco, Mercor, NU, monday.com, Nvidia, Bridgewater, LinkedIn, Coinbase, Bristol Myers Squibb, Rakuten, ServiceNow, Elastic, Uber, Exa, Cogent, Serval, Zip, Listen, Harmonic and Abridge.
How LangGraph works
- Install LangGraph via pip or npm, or use LangChain's
create_agentharness on top of it. Define the agent as a graph of nodes (model calls, tools, sub-agents) connected by edges that control flow, including cycles. - Wire up checkpointed persistence with Postgres, SQLite or Redis, add a cross-thread memory store where needed, and insert human-in-the-loop interrupts at the points where a person should review or steer.
- Deploy through LangSmith for one-click deployment, autoscaling and tracing. Use time-travel debugging to replay any checkpoint when something goes wrong in production.
Key features
- Cyclical graph execution
- Agents are defined as nodes and edges with conditional branches and cycles. An agent can loop, retry and revisit earlier steps instead of only running as a straight-line chain.
- Checkpointed persistence
- State is saved after every node transition under a thread_id, with Postgres, SQLite or Redis backends, so a run survives a restart and resumes exactly where it left off.
- Time-travel debugging
- Any prior checkpoint can be replayed or resumed, letting a developer step back through an agent's execution history to find where it went wrong.
- Human-in-the-loop interrupts
- A graph can pause mid-run so a person can inspect or edit its state before the agent continues, without losing progress.
- Cross-thread memory (stores)
- A separate store layer persists application-defined data across conversations, distinct from the thread-scoped checkpoint state.
- Native token-by-token streaming
- Agent reasoning and tool calls stream in real time rather than returning only a final answer.
- Supervisor / subagent multi-agent pattern
- A supervisor node coordinates subagents by calling them as tools and combining their outputs, with each subagent able to run in its own subgraph with a private message history.
- LangSmith deployment and tracing
- LangSmith adds an Assistants API with over 30 endpoints, one-click deployment, autoscaling, tracing, evaluation, an LLM Gateway, an Engine, Sandboxes and a no-code Fleet builder.
What are LangGraph's use cases?
- Production customer-support agent at scale
- A support team builds an agent that has to reliably handle millions of users, survive process restarts mid-conversation, and let a human step in on edge cases. Klarna is named on the LangGraph trusted-by strip for this kind of deployment.
- Large-scale automated code migration
- An internal developer-platform team runs a network of agents that plan and execute code migrations and generate unit tests across a large codebase. Uber is named on the trusted-by strip for developer-platform work in this shape.
- Multi-agent research or recruiting workflow
- A hierarchical system of agents, with a supervisor coordinating specialist subagents, handles conversational search and candidate matching. LinkedIn is named on the trusted-by strip for this kind of multi-agent system.
- Customer support workflow with human approval
- A support team adds a human-in-the-loop checkpoint so an agent drafts a response but a person approves refunds or account changes before they execute.
- Production agent with tracing and replay
- A startup ships an agent via LangSmith's one-click deployment and traces requests in production. Time-travel debugging lets the team replay any prior checkpoint to find where a run went wrong.
Who is LangGraph for?
- Engineering teams building stateful or multi-agent systems who need loops, retries and durable execution.
- Teams already using LangChain who want more control over state, interrupts and replay than the quick-start harness exposes.
- Startups needing a path to production deployment, tracing and evaluation alongside the open-source framework.
Not forTeams that want to ship a first working agent in under an hour, do not need graph-level control over state and branching, or are building a lightweight TypeScript app on serverless infrastructure where a framework like Mastra fits the deploy target better.
What does LangGraph integrate with?
- OpenAI
- Anthropic
- AWS Bedrock
- Groq
- Ollama (local models)
- Model Context Protocol via langchain-mcp-adapters
- LangSmith (tracing, evaluation, deployment)
- LangGraph Studio (visual debugger)
- Postgres / SQLite / Redis (checkpoint backends)
Why use LangGraph?
- MIT-licensed and free at the core, with no usage fees for the open-source library itself.
- Cyclical graphs with built-in checkpointing, time-travel debugging and human-in-the-loop interrupts are native, not add-ons.
- 30+ named production customers on the vendor's trusted-by strip as of 2026-08-23, including Klarna, LinkedIn, Uber and Elastic.
- Cross-thread memory stores, token-by-token streaming and a supervisor/subagent pattern are built in rather than bolted on.
What are LangGraph's pros and cons?
What's great
- Checkpointed state at every node transition means a production agent can survive a restart, resume where it left off, and be replayed from any earlier checkpoint for debugging.
- Explicit graph structure makes every state transition visible and testable, rather than hidden inside a role-based or implicit abstraction.
- Native human-in-the-loop interrupts let a person inspect or edit an agent's state mid-run without losing progress.
- Named production adoption at scale on the vendor's own trusted-by strip, including Klarna, LinkedIn, Uber and Elastic.
- Actively maintained Python and JavaScript libraries, MIT-licensed, with public GitHub releases.
Watch-outs
- Production costs add up through usage-based LCU and LSU units on top of seat fees. A small setup can run from tens of dollars into the low hundreds per month before any LLM API costs, depending on trace volume and deployment size.
- Independent reviewers consistently describe a steep learning curve, with documentation split across the LangGraph, LangChain and LangSmith sites.
- The explicit graph model means refactoring an agent often means redrawing the graph. Independent reviewers report longer onboarding onto a LangGraph codebase than most alternatives.
- Not a no-code tool. Non-technical teams need LangChain's separate Fleet product on LangSmith or another platform.
- Managed deployment is not designed for serverless platforms like Vercel or Cloudflare Workers, unlike TypeScript-native competitors such as Mastra.
- No native token-budget or cost-limit management in the framework. Cost caps have to be handled at the model-integration level.
- Managed deployment (LangSmith) is not designed to run on serverless platforms like Vercel or Cloudflare Workers.
- Documentation is split across the LangGraph, LangChain and LangSmith sites, which independent reviewers cite as a real onboarding cost.
LangGraph pricing
Developer is free for 1 seat with 5,000 traces/month. Plus is $39/seat/month with 10,000 traces and one free Serverless Small deployment. Enterprise is custom. Usage is metered separately in LCUs ($1.50 each) and LSUs ($1.00 each).
Developer
$0/seat/month
- 1 seat
- Up to 5,000 base traces per month, then pay-as-you-go
- Community support
- 5 LCU of Fleet usage and 5 LCU + 1 LSU of Sandbox usage included each month
Plus
$39/seat/month
- Unlimited seats
- Up to 10,000 base traces per month, then pay-as-you-go
- One free Serverless (Small) deployment included. Additional Serverless and Dedicated deployments billed by resources consumed (Runtime Compute 0.045 LCU/vCPU-hr, Runtime Memory 0.006 LCU/GiB-hr, Database Compute 0.177 LSU/vCPU-hr, Database Memory 0.025 LSU/GiB-hr)
- Engine, Tuned Evaluators, Fleet (25 LCU/mo included) and LLM Gateway controls included. Sandboxes included at 5 LCU + 1 LSU per month
- Email, portal and community-forum support
Enterprise
Custom
- Self-hosted and hybrid deployment options
- Custom SSO, ABAC and RBAC
- Support SLA
- Custom seats and workspaces
See current pricing on langchain.com ↗Compare LangGraph alternatives →
Frequently asked questions
Is LangGraph free to use?
Does LangGraph have a visual, no-code builder?
What does LangGraph cost in production?
Which model providers does LangGraph work with?
Who uses LangGraph in production?
What is the difference between LangChain and LangGraph?
LangGraph alternatives
- LangChain
LangGraph's own parent library. Use LangChain's create_agent for a batteries-included quick start, and reach for LangGraph when you want direct control of the state, nodes and checkpoints underneath.
- CrewAI
A faster, role-based path to a working multi-agent crew. It trades LangGraph's explicit graphs and checkpointing for a higher-level abstraction that ships in under an hour.
- Mastra
The TypeScript-native equivalent, with first-class Vercel, Cloudflare and Netlify serverless deploy targets that LangGraph's Python-first, always-on execution model does not offer.
- Pydantic AI
A lighter, type-safety-first Python SDK for validating a single model's structured output. The right fit when the problem is not multi-step graph orchestration at all.
- Compare the whole category
Every agent in Agent frameworks, side by side on the same fields.
Anything to add?
This page is researched and re-verified by our editors — but the people who actually use LangGraph know things we cannot see from the outside.
Report an issueSomething wrong, outdated or a dead link? Tell us and we re-verify.
Write a reviewUsed LangGraph? Your experience helps the next buyer decide.
Get a quote from LangGraphTell us what you need and we make the introduction.
Get weekly Agent frameworks updates
New agents and fresh verdicts. One short email, every week. One-click unsubscribe.