langgraph
by langchain-ai
LangGraph is a Python framework for building AI agents and workflows that keep their state, can run for a long time and can resume after failures. It is aimed at developers who want fine control over how agents plan, remember and involve a human.
- Stars
- 44k +39 a day
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Technical
- Language
- Python
- Age
- 1174 days
What you can do with it
- Build AI agents that remember earlier conversations and carry on across sessions
- Add human approval steps so a person can check or edit an agent's work mid-run
- Create multi-step or multi-agent workflows that resume from where they stopped after a failure
Make money with it
A freelance developer could build and maintain custom AI agent workflows for clients who need automation tailored to their business.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build a customer support or internal helper agent that hands tricky cases to a person for approval
- Automate multi-step back-office tasks such as research, document processing or report drafting with a recoverable workflow
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install it as a Python package with "pip install -U langgraph", then write your own code using the documentation.
Follow the official instructions in the project README.
Things to check
- Low-level library that needs programming skill, not a ready-made app
- Needs a language model provider, which usually means paid API keys
- Debugging and hosted deployment tools (LangSmith) are separate and may be paid
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
