---
title: "LangGraph"
url: "/docs/proxy/lens/integrations/langgraph"
canonical_url: "https://docs.litellm.ai/docs/proxy/lens/integrations/langgraph"
type: "docs"
last_updated: "2026-10-03"
summary: "Run LangGraph examples and send their agent traces to LiteLLM Lens."
related:
  - "/docs/proxy/lens/integrations/deepagents"
  - "/docs/proxy/lens/integrations/langchain"
---
# LangGraph

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt

<!-- Generated from BerriAI/litellm-lens-example/langgraph/README.md at a6cce7983ec78ef9183627a0b05e0e3ce548b98a. Edit the source README. -->

# LangGraph

Send LangGraph traces to [LiteLLM Lens](/docs/proxy/lens) using the runnable examples in this repository.

## Prerequisites

You need a LiteLLM gateway with [tracing enabled](/docs/proxy/lens/deployment#configure-an-existing-proxy), a LiteLLM key, and a configured model alias. A Lens worker is required for investigations; viewing traces does not require one.

Install uv. It uses the checked-in Python version and resolves each example’s dependencies from its uv workspace.

## Configuration

For a fresh checkout:

```bash
git clone https://github.com/BerriAI/litellm-lens-example.git
cd litellm-lens-example/langgraph
cp .env.example .env
```

If you already cloned the repository, run the remaining commands from `langgraph/`. Copy [.env.example](https://github.com/BerriAI/litellm-lens-example/blob/a6cce7983ec78ef9183627a0b05e0e3ce548b98a/langgraph/.env.example) to `.env` if it does not exist, then set:

| Variable              | Value                                                                                          |
| --------------------- | ---------------------------------------------------------------------------------------------- |
| `LITELLM_GATEWAY_URL` | Your gateway’s base URL without a trailing slash or `/v1`, for example `http://localhost:4002` |
| `LITELLM_API_KEY`     | Your LiteLLM key                                                                               |
| `LITELLM_MODEL`       | A model alias configured on your gateway                                                       |

The checked-in values target a local development gateway. Replace them for your deployment. Keep the exporter settings from `.env.example`; the examples configure their trace exporters in code. They send traces to `LITELLM_GATEWAY_URL/v1/traces` with the LiteLLM key as a bearer token.

Leave `MOCK_LITELLM_GATEWAY_URL` unset unless you intend to send an additional trace copy to the local [recorder](https://github.com/BerriAI/litellm-lens-example/blob/a6cce7983ec78ef9183627a0b05e0e3ce548b98a/recorder/AGENTS.md).

## Run an example

### Simple agent

A single-node graph answers one question.

```bash
uv run --env-file .env --package lens-langgraph-simple simple/main.py
```

See [simple/main.py](https://github.com/BerriAI/litellm-lens-example/blob/a6cce7983ec78ef9183627a0b05e0e3ce548b98a/langgraph/simple/main.py) for the implementation.

### Agent swarm

A `research_agent` graph runs `search_agent` and `writer_agent` subgraphs.

```bash
uv run --env-file .env --package lens-langgraph-swarm swarm/main.py
```

See [swarm/main.py](https://github.com/BerriAI/litellm-lens-example/blob/a6cce7983ec78ef9183627a0b05e0e3ce548b98a/langgraph/swarm/main.py) for the implementation.

## Verify the trace

After the example prints its answer, open **Lens > Traces** on your gateway and select the new run. Look for the run associated with `research_agent`. Inspect the input, output, and model spans. For the swarm, inspect the specialist activity described above; its exact span layout depends on the framework.

## How tracing works

OpenInference instruments the compiled graph and its nodes. Each specialist is a compiled subgraph; its wrapper node uses a distinct name to avoid counting the same agent twice.

## Troubleshooting

If model calls fail, check the gateway URL, key, and model alias. If an answer appears but the trace is missing, check the terminal for exporter errors and confirm tracing is enabled on the same gateway. A model call succeeding does not confirm that its trace export succeeded.

## Related pages

- [DeepAgents](https://docs.litellm.ai/docs/proxy/lens/integrations/deepagents.md)
- [LangChain](https://docs.litellm.ai/docs/proxy/lens/integrations/langchain.md)