LangGraph
Open source · Agents and frameworks · langchain-ai/langgraph
What it does
LangGraph is a library for agents that need several steps, branches or loops. You describe the agent as a graph of steps, and it keeps track of state so a run can pause, wait for a person to approve, and carry on.
Good for: Building agents that must be reliable over long, multi-step tasks, with a human check in the middle.
LangGraph on GitHub (opens in a new tab) Project homepage (opens in a new tab)
Visitor votes, one per browser. Your own vote is kept on this device only. How votes work.
The signals we checked
- Licence
- MIT (OSI-approved open-source licence)
- Popularity
- Stars: 43,336 (checked 16 Oct 2026)
- Last commit
- 16 Oct 2026
- Open issues and PRs
- 811
- Status
- Active (not archived)
- Self-host
- ModerateA code library for Python or JavaScript.
- GitHub topics
- agents
- ai
- ai-agents
- chatgpt
- deepagents
- enterprise
- framework
- gemini
- generative-ai
- langchain
More in agents and frameworks
- LangChain Developers who want a standard toolkit to build an AI feature or agent in Python or JavaScript.
- Browser Use Automating repetitive website tasks that have no API, such as filling in the same form many times.
- OpenHands Handing a contained coding task to an agent while keeping it inside a sandbox.
- CrewAI Splitting a job such as research then drafting then review across several agents.
No affiliate links on this page, and we are not paid by this project. The summary is our own plain-English description; check the repo for current features before you rely on it.
Stars, licences and commit dates come from the GitHub API, checked 16 Oct 2026. "Last commit" is the last push to the repo. Star counts are a rough popularity signal, not a quality score. There are no affiliate links in this section: links go straight to each project.