Updated

LangGraph

Open-source framework from the LangChain team for building stateful, long-running agents as graphs of steps, with persistence, human-in-the-loop and streaming, in Python and JavaScript.

120 open-source projects declare LangGraph in their code; 1 maker's product we track uses it. What makers like most: Explicit stateful graphs with checkpointing and human-in-the-loop steps give control over every step of an agent. Their most common complaint: Graph-based orchestration can turn into technical debt as models improve, and plain agent loops beat it in some teams' evals. On GitHub, 6 public pull requests moved projects to LangGraph from tools we list, and 8 moved them away.

Open sourceSelf-hostableFree tierPaid from $39/seat/mo (LangSmith Plus, includes one small deployment)

Profile checked

Works with AI agents:llms.txtCLI
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use LangGraph

Makers' products we track use LangGraph for AI SDK & agent framework (1).

What LangGraph is used for

AI SDK & Agent Framework · Multi-agent orchestration →Stateful agents built as an explicit graph of steps, with checkpoints, retries, streaming and pauses for human approval, in Python or JavaScript.Trade-off: Lower-level than a prebuilt agent — you design the graph and state yourself; managed deployment and tracing sit in paid LangSmith plans.
LangChain66Mastra24LlamaIndex16AI SDK5CrewAI3LangGraph1Makers' products on each, for AI SDK & agent framework

LangGraph vs the alternatives makers chose

For AI SDK & agent framework, 1 of the 115 makers' products we know the choice of picked LangGraph (1%), behind LangChain (57%).

OptionMakers' productsOpen source
LangChain66 57%Yes
Mastra24 21%Yes
LlamaIndex16 14%Yes
AI SDK5 4%Yes
CrewAI3 3%Yes
LangGraph1 1%Yes

For AI SDK & agent framework: how many of the 115 makers' products we know the AI SDK & agent framework of chose each option.

When to use LangGraph, and when not

Pick LangGraph if

Something else fits better if

  • Your app is TypeScript and you want agents without adding a Python service: AI SDK or Mastra.
  • You want a small typed agent loop in Python, close to the raw API: Pydantic AI or OpenAI Agents SDK.
  • Your agent works on files and runs commands, like a coding or research agent: Claude Agent SDK.
  • You need many prebuilt connectors for models, tools and data sources: LangChain.
  • The agent mostly retrieves and reasons over your own documents: LlamaIndex.
From each decision's guide, written from what makers' products chose and why.

LangGraph is an open-source orchestration library for agents that run many steps, run for a long time, or need a person to step in. You describe the agent as a graph: nodes are functions (an LLM call, a tool call, or ordinary code), edges decide what runs next, and a shared state object flows between them. Deterministic steps and model-driven steps live in the same graph.

More about LangGraph

The model a developer has to understand is the state graph plus checkpoints. You define a state schema, add nodes and edges, and compile the graph. Compiled with a checkpointer, LangGraph saves the state after each step under a thread id, which is what lets a run pause for human approval, resume after a crash, or be rewound. Libraries exist for Python and JavaScript/TypeScript; LangChain is optional.

What a small team gets: durable execution, streaming of intermediate steps, interrupts for human-in-the-loop, short-term memory per thread and a separate store for long-term memory across threads. Checkpointers come for SQLite (local work) and Postgres or MongoDB (production). It works with any model, including open-weight ones. You run it in your own app, or deploy it on LangSmith Deployment, which runs as cloud, bring-your-own-cloud or self-hosted.

It is deliberately low-level: it does not hand you prompts or an agent architecture. The LangChain team points people who want a prebuilt tool-calling loop to LangChain's agents instead. Without LangSmith, you run the persistence database, scaling and retries yourself.

How LangGraph itself is built

5 tools, from its own code, website and Product Hunt page.

LangGraph pros and cons

What makers like most: Explicit stateful graphs with checkpointing and human-in-the-loop steps give control over every step of an agent. Their most common complaint: Graph-based orchestration can turn into technical debt as models improve, and plain agent loops beat it in some teams' evals.

Pros

  • Explicit stateful graphs with checkpointing and human-in-the-loop steps give control over every step of an agent. PHHNHN 2
  • Nodes put fences around what the model may do, so a defined workflow is followed reliably. HNHN 2
  • Checkpointing and state management save teams from the edge-case bugs of a homegrown version. HNHN 2

Cons and watch-outs

  • Graph-based orchestration can turn into technical debt as models improve, and plain agent loops beat it in some teams' evals. HNHN 2
  • It adds complexity, and some teams find a homegrown harness fits their stack better. HNHN 2

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

Reliability and open issues

The most wanted open issue on GitHub has 12 👍.

Most wanted on GitHub

Open on 2026-10-04 in langchain-ai/langgraph, with activity in the last year — issues and feature requests by 👍.

Who switches

More projects move away from LangGraph: 6 pull requests in, 8 out; the most come from LangChain and leave for Mastra.

Moving to LangGraphMoving away
LangGraph
LangChain → LangGraph6+ PRs
LangGraph → Mastra5 PRs
LangGraph → LangChain3+ PRs

Public pull requests on GitHub since Oct 2024 whose title says "X to Y" — real code changes moving a project from one tool to another, by developers in general.

Who uses it

1 makers' products, each linked to the source that shows it, and 120 open-source projects that declare it in their code. The best known on Product Hunt: Semos.ai Manager Agents (480 followers).

The maker says so 1Declared in code 120How evidence is collected →
Semos.ai Manager Agents
Semos.ai Manager AgentsAI agents purpose-built for managers

“We picked LangGraph over CrewAI and AutoGen because it gives us explicit, stateful agent graphs with checkpoints and human approval steps, so we control every step instead of hoping the agents behave.”

AI SDK & Agent FrameworkMaker says so · source ↗
Agno
AgnoOpen-source Python agent framework and runtime (AgentOS) that you run in your own cloud,…AI SDK & Agent FrameworkIn its code · source ↗
Aix-DB
Aix-DBAix-DB 基于 LangChain/LangGraph 框架,结合 MCP Skills 多智能体协作架构,实现自然语言到数据洞察的端到端转换。AI SDK & Agent FrameworkIn its code · source ↗
n8n
n8nWorkflow automation tool with a visual node editor, code steps and AI agent nodes, avail…AI SDK & Agent FrameworkIn its code · source ↗
Novu
NovuNotification infrastructure for sending multi-channel messages (email, in-app, SMS, chat…AI SDK & Agent FrameworkIn its code · source ↗
omi
omiOpen-source AI wearable with mobile and desktop apps that records conversations and meet…AI SDK & Agent FrameworkIn its code · source ↗
Opik
OpikOpen-source LLM tracing, evaluation and prompt optimization platform from Comet, self-ho…AI SDK & Agent FrameworkIn its code · source ↗
prisma-ai
prisma-ai你的求职AI co-pilot,优化你的项目,定制你的简历,为你匹配工作,并帮助你做好面试准备。此外,还提供一个免费的面经导向的面向offer学习网站:https://pink…AI SDK & Agent FrameworkIn its code · source ↗
refly
reflyThe first open-source agent skills builder. Define skills by vibe workflow, run on Claud…AI SDK & Agent FrameworkIn its code · source ↗
Yuxi
Yuxi可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG…AI SDK & Agent FrameworkIn its code · source ↗

Open source: a project that declares LangGraph as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

49 of the 85 open-source products built with LangGraph that were worked on in the last 180 days keep instruction files for coding agents — 58%, against 53% of all the projects we read. AGENTS.md is in 39, CLAUDE.md in 29.

1,174words in the median file
uvthe package manager most named, in 16 of 42 files
71%say how to test a change
Named more in these files than in other projects' — in how many of the 42:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to LangGraph

All alternatives by situation →

Further reading

Questions makers ask about LangGraph

What is LangGraph used for?

Open-source framework from the LangChain team for building stateful, long-running agents as graphs of steps, with persistence, human-in-the-loop and streaming, in Python and JavaScript. Makers' products we track use it for AI SDK & agent framework (1).

What are the pros and cons of LangGraph?

Pros makers name: Explicit stateful graphs with checkpointing and human-in-the-loop steps give control over every step of an agent. Nodes put fences around what the model may do, so a defined workflow is followed reliably. Checkpointing and state management save teams from the edge-case bugs of a homegrown version. Cons: Graph-based orchestration can turn into technical debt as models improve, and plain agent loops beat it in some teams' evals. It adds complexity, and some teams find a homegrown harness fits their stack better.

What are the alternatives to LangGraph?

For AI SDK & agent framework, the other options makers' products we track chose most are LangChain (66), Mastra (24), LlamaIndex (16), AI SDK (5), CrewAI (3). Open source or self-hostable among them: LangChain, Mastra, LlamaIndex, AI SDK, CrewAI. Each alternative, with the situation it fits, is on the LangGraph alternatives page.

Do developers switch to or away from LangGraph?

On GitHub, 6 public pull requests moved projects to LangGraph from tools we list, most from LangChain (6); 8 moved them away, most to Mastra (5), LangChain (3).

When should you use LangGraph?

Your agent is a long-running workflow with branches, saved state and human approval steps (AI SDK & agent framework). Something else fits better if: your app is TypeScript and you want agents without adding a Python service, pick AI SDK or Mastra; you want a small typed agent loop in Python, close to the raw API, pick Pydantic AI or OpenAI Agents SDK.

Do I need LangChain to use LangGraph?

No. LangGraph is a lower-level orchestration library and can be used on its own; LangChain components are optional helpers for models and tools. source ↗

Does it work with open-source models or models without tool calling?

Yes. It does not depend on a particular model. With a model that lacks tool calling you write a little code to turn its text output into the next decision. source ↗

What do I need to self-manage if I don't use LangSmith?

The open-source library leaves persistence, deployment, scaling, retries and monitoring to you, and has no HTTP API or cron scheduling. LangSmith Deployment adds managed Postgres persistence, auto-scaling task queues, cron and an HTTP API for state. source ↗

Which databases can store agent state?

Official checkpointers cover in-memory, SQLite (recommended for experiments), and Postgres or MongoDB for production; an Azure Cosmos DB checkpointer is also available. Each is a separate package. source ↗

Can I deploy it on my own infrastructure?

Yes. You can run the library inside any app you host, or use LangSmith Deployment on cloud, bring-your-own-cloud or your own infrastructure, all using the same Agent Server runtime. source ↗

Can I use the visual Studio debugger without a LangSmith account?

Yes. Run the local development Agent Server and connect it to Studio; set LANGSMITH_TRACING=false and no traces are sent to LangSmith. source ↗

Is JavaScript a first-class option?

Yes. LangGraph has Python and JavaScript/TypeScript libraries with the same core concepts; the JS package is @langchain/langgraph. source ↗

Is LangGraph free?

Yes — there is a free tier a small product can run on; paid use starts at $39/seat/mo (LangSmith Plus, includes one small deployment). source ↗

Is LangGraph open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with LangGraph?

It serves an llms.txt docs index; it has an official CLI (@langchain/langgraph-cli).

Who uses LangGraph?

1 makers' products we track, each with a source, and 120 open-source projects declare it in their code. The best known of them on Product Hunt: Semos.ai Manager Agents (480 followers). source ↗