Agent Inbox Langgraph Example

Agent Inbox LangGraph Example

The repository contains a bare minimum code example to get started with the Agent Inbox with LangGraph.

[!TIP] Looking for the TypeScript version of this example repository? Click [here](https://github.com/langchain-ai/agent-inbox-langgraphjs-example)

Getting Started

To get started, clone the repository:

git clone https://github.com/langchain-ai/agent-inbox-langgraph-example.git

cd agent-inbox-langgraph-example

Then, install the dependencies:

poetry install

Next, install the [LangGraph CLI](https://langchain-ai.github.io/langgraph/cloud/reference/cli/) if not already installed. We're installing the in-memory version so we can run the LangGraph server without Docker.

pip install -U "langgraph-cli[inmem]"

After this, we can start the LangGraph server:

langgraph dev

This may take a second to start. Once the server is running, it should open a new browser tab to the LangGraph Studio through LangSmith. If this does not happen automatically, visit this URL: [https://smith.langchain.com/studio/thread?baseUrl=http%3A%2F%2F127.0.0.1%3A2024](https://smith.langchain.com/studio/thread?baseUrl=http%3A%2F%2F127.0.0.1%3A2024)

Now that our LangGraph server is running, we can start a new run in the Studio. To do this, simply enter any string into the `Interrupt Response` field, then click the `Submit` button. This will execute the graph, and interrupt on the `human_node`. Once the graph has interrupted, we can visit the Agent Inbox site to add your graph, and manage the interrupted thread.

Agent Inbox Setup

Visit [`dev.agentinbox.ai`](https://dev.agentinbox.ai). If it's your first time visiting the site, you'll be prompted to add a new graph.

Enter the following fields into the form:

• Graph/Assistant ID: agent - this corresponds to the ID of the graph defined in the `langgraph.json` file, or the ID of an assistant tied to your graph.
• Deploy