Find tools › Open-source projects › Automate busywork

langgraph

Open-source project · by langchain-ai

A Python toolkit for programmers to build AI helpers that work through many steps over time.

For developersPopular60,374,924 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Build an agent that follows a multi-step business process
  • Pause an AI workflow for human approval, then resume
  • Keep an agent's progress saved across long tasks

How to start

  1. Install Python if you do not have it.

  2. In a terminal, run pip install -U langgraph.

  3. Follow the README quickstart to build a small agent in Python.

  4. The paid LangSmith services are optional; the library works without them.

Good to know. It is intentionally low-level, so expect a learning curve. The README steers you toward LangChain's paid LangSmith tracing and deployment services, but the MIT-licensed library works without them.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

A low-level Python library (with a JS version) from LangChain Inc for building long-running, stateful AI agents as graphs of steps.

Use it when you are writing code for an agent that has to survive crashes and resume where it stopped, pause for human approval, or keep memory across sessions. For a quicker start, the README points to its higher-level 'Deep Agents' package.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map