> ## Documentation Index
> Fetch the complete documentation index at: https://docs.egma.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Monitor a LiveKit agent

LiveKit monitoring sends conversation evidence from your worker through the Egma SDK. You do not need a test suite or simulation connection.

## Start through the UI

1. Open **Agents → Connect an agent**.
2. Choose **Monitor production**, then select **Continue**.
3. Select **LiveKit** and follow the setup prompts.

Add the project key and SDK hook to your worker using the steps below. Opening the wizard alone does not enable monitoring.

## Create an Egma project key

In your initialized agent repository, run:

```bash theme={"system"}
egma project api-key create --name "LiveKit monitoring"
```

Copy the key when the CLI prints it. The CLI shows it once and does not save
it. You can also create a key in **Settings → API keys**.

Add these environment variables to the worker through your normal deployment
secret store:

| Variable       | Value                                                                                  |
| -------------- | -------------------------------------------------------------------------------------- |
| `EGMA_URL`     | `https://app.egma.ai` for hosted Egma, or the public URL of your self-hosted instance. |
| `EGMA_API_KEY` | The project API key you just created.                                                  |

The worker must be able to reach `EGMA_URL`. `localhost` refers to the worker's
own machine or container, so use a reachable address for a remote deployment.

## Add the monitoring hook

<Tabs>
  <Tab title="Python">
    Install the [LiveKit Python SDK](/skills-cli-sdks/sdks/livekit-python):

    ```bash theme={"system"}
    uv add 'egma @ git+https://github.com/egma-ai/egma.git#subdirectory=sdks/python'
    ```

    Add this import to the file that defines your job entrypoint:

    ```python theme={"system"}
    from egma import monitor
    ```

    Make this the first statement inside the entrypoint, before `ctx.connect`
    or `AgentSession.start`:

    ```python theme={"system"}
    monitor(ctx)
    ```

    This requires Python 3.11 or newer and `livekit-agents>=1.6.6,<1.9`.
  </Tab>

  <Tab title="JavaScript">
    Install the [LiveKit JavaScript SDK](/skills-cli-sdks/sdks/livekit-javascript):

    ```bash theme={"system"}
    npm install @egma/livekit
    ```

    Add this import to your worker:

    ```typescript theme={"system"}
    import { monitor } from "@egma/livekit";
    ```

    Call the hook at the start of the job entrypoint, before starting the
    `AgentSession`:

    ```typescript theme={"system"}
    monitor(ctx);
    ```

    Monitoring requires Node.js 22 or newer and `@livekit/agents>=1.5.5 <2`.
  </Tab>
</Tabs>

Apply the code and environment variables to the worker that handles real
conversations, then restart or redeploy that worker. The hook adds Egma export
alongside a compatible existing OpenTelemetry setup, including LiveKit Cloud
observability. It sends spans in batches and flushes the final batch when the
job ends.

The hook ignores rooms whose names start with `egma-sim-`, so your tests do not
also appear as production conversations. The separate `simulation` hook sends
those rooms' evidence to their simulation records. Use both hooks when the
same worker handles testing and production; both use the same Egma settings.
Keep the `egma-sim-` prefix reserved when naming your own production rooms.

## Verify a conversation

Complete one normal conversation with the updated worker, then open
**Traces** in the project that owns the API key. Open the new trace and
check its transcript and timing.

There is no LiveKit monitoring switch to enable in Egma. The first received
trace confirms that the worker can send evidence to Egma. If no conversation
appears, check the worker's OpenTelemetry logs, the project key, and network
access to `EGMA_URL`.

To stop this worker from sending new production evidence, remove its `monitor`
call and restart the worker. Existing conversations stay in Egma. Keep
`simulation` if the worker still handles Egma tests.

## Review the evidence

[Review production conversations](/docs/platform/monitoring/review-conversations) to inspect transcripts, metrics, and grades.