DEDUPEDWhat do you want to do?
3 use cases
-
Build an agent that resumes after a crash
Use LangGraph's durable execution so a long agent run picks up exactly where it stopped.
View prompt
Using langchain-ai/langgraph, build a <describe agent> as a graph with durable execution, following the official Quickstart and Durable execution docs. Then show me that if I stop the process halfway, rerunning it resumes from the last completed step instead of starting over.
-
Pause an agent for human approval before it acts
Use LangGraph interrupts to inspect and edit an agent's state before a risky step runs.
View prompt
With langchain-ai/langgraph, add a human-in-the-loop interrupt before the <risky action> step of my agent. When it pauses, print the pending state, let me edit it, and only resume after I approve.
-
Give an agent memory that lasts across sessions
Combine short-term working memory and long-term memory so an assistant remembers users between conversations.
View prompt
Using langchain-ai/langgraph, give my <assistant> short-term memory for the current conversation and long-term memory keyed by user, following the Comprehensive memory docs. Demonstrate it remembering a fact from a previous session.
Quick start with Langgraph
- Check you have what it needs: Python and pip; An LLM provider for your agent's model calls; Optional: a LangSmith account for tracing and the LangSmith Deployment platform.
- Open langchain-ai/langgraph on GitHub and read the README and license.
- Install the library with
pip install -U langgraph - Work through the LangGraph Quickstart in the docs to define your agent as a graph of steps
- Add persistence following the Durable execution guide so each step's state is saved
- Kill the process mid-run, restart it and confirm it continues from the last saved step
These steps come from our top use case, Build an agent that resumes after a crash, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for langchain-ai/langgraph
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forPython developers who need agents that run for a long time, survive failures and pause for human review, rather than a single prompt loop.
- Why it is hot44k stars, talked about in 2 AI sources we track
- LanguagePython
- Sourcegithub.com/langchain-ai/langgraph ยท Back to Hot repos
Requirements
- Python and pip
- An LLM provider for your agent's model calls
- Optional: a LangSmith account for tracing and the LangSmith Deployment platform
- For JavaScript or TypeScript, the separate LangGraph.js library
Add this badge to your README
Maintain Langgraph? Show readers where to find these use cases. 
Markdown
[](https://dedupedai.com/use-cases/langchain-ai-langgraph/?utm_source=github&utm_medium=badge&utm_campaign=langchain-ai-langgraph)
HTML
<a href="https://dedupedai.com/use-cases/langchain-ai-langgraph/?utm_source=github&utm_medium=badge&utm_campaign=langchain-ai-langgraph"><img src="https://dedupedai.com/badge/langchain-ai/langgraph.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Langgraph
What is Langgraph?
LangGraph is a low-level orchestration framework from LangChain for building, managing and deploying long-running, stateful agents. It provides durable execution that resumes from where a run left off, human-in-the-loop checkpoints to inspect and modify agent state, short-term and long-term memory, debugging through LangSmith, and production deployment. It can be used without LangChain, and Deep Agents is a higher-level package built on top of it. It is an open-source project on GitHub: https://github.com/langchain-ai/langgraph.
How do I use Langgraph?
Install the library with pip install -U langgraph; then Work through the LangGraph Quickstart in the docs to define your agent as a graph of steps; add persistence following the Durable execution guide so each step's state is saved. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Langgraph for?
Python developers who need agents that run for a long time, survive failures and pause for human review, rather than a single prompt loop.
What can I do with Langgraph?
3 use cases so far, for example: Build an agent that resumes after a crash; Pause an agent for human approval before it acts; Give an agent memory that lasts across sessions. Each has steps and a copy-paste agent prompt.
What do I need to run Langgraph?
Python and pip; An LLM provider for your agent's model calls; Optional: a LangSmith account for tracing and the LangSmith Deployment platform; For JavaScript or TypeScript, the separate LangGraph.js library.
What are alternatives to Langgraph?
Other hot AI repos in Software and DevOps: Deep Infer, Thinkrail, ECC, Instructor, Aider.
Is Langgraph safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.