OpenClaw Observability & Monitoring with OpenTelemetry

What is OpenClaw Observability?

OpenClaw observability gives you real-time visibility into your LLM applications and AI workflows by collecting traces, logs, and metrics using OpenTelemetry. This guide shows you how to instrument OpenClaw and send telemetry data to SigNoz, so you can monitor performance, debug issues, and optimize your AI workflows.

With full OpenClaw observability in SigNoz, you can correlate traces, logs, and metrics in a single dashboard, set up alerts for error rates or high latency, and analyze LLM usage patterns over time to continuously improve reliability and efficiency.

Prerequisites

A SigNoz Cloud account with an active ingestion key or Self Hosted SigNoz instance
For Python: pip installed for managing Python packages
A running OpenClaw instance

Monitor OpenClaw with OpenTelemetry

For more information on getting started with OpenClaw in your environment, refer to the OpenClaw quickstart guide.

Current version of OpenClaw still has some issues with log ingestion. To enable it we have made some changes in a forked repo and created a PR#22478. Feel free to follow below steps to enable logs. If you just want traces and metrics then you can ignore these steps.

Preconditions

Node.js and pnpm are installed.
Your npm global prefix is set to a user-level directory (e.g., ~/.npm-global).

Clone the Repository & Checkout the Fix Branch

git clone https://github.com/LuffySama-Dev/openclaw.git
cd openclaw
git switch logsIsolationIssueFixed

Install dependencies and build

pnpm install
pnpm build

Install globally from the local repo (important: do not use sudo)

npm install -g .

Ensure the user-level npm bin directory is first in your PATH

echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc
hash -r

Verify that OpenClaw resolves to the user path (not /usr/bin)

which openclaw
openclaw --version
npm ls -g openclaw --depth=0

Step 1: Enable Diagnostic-OTel plugin

The diagnostics-otel plugin ships with OpenClaw but is disabled by default. You can enable it via CLI:

openclaw plugins enable diagnostics-otel

Or add it directly to your config file (~/.openclaw/openclaw.json):

{
  "plugins": {
    "allow": ["diagnostics-otel"],
    "entries": {
      "diagnostics-otel": {
        "enabled": true
      }
    }
  }
}

Step 2: Configure the OTEL Exporter

You can configure the exporter via CLI:

openclaw config set diagnostics.enabled true
openclaw config set diagnostics.otel.enabled true
openclaw config set diagnostics.otel.traces true
openclaw config set diagnostics.otel.metrics true
openclaw config set diagnostics.otel.logs true
openclaw config set diagnostics.otel.protocol http/protobuf
openclaw config set diagnostics.otel.endpoint "https://ingest.<region>.signoz.cloud:443"
openclaw config set diagnostics.otel.headers '{"signoz-ingestion-key":"<your-ingestion-key>"}'
openclaw config set diagnostics.otel.serviceName "<service_name>"

<service_name> is the name of your service
<region>: Your SigNoz Cloud region
<your-ingestion-key>: Your SigNoz ingestion key

Step 3: Check your config (Optional)

You can quickly check your config using the following command:

openclaw config get diagnostics

Your output should look like this.

{
  "enabled": true,
  "otel": {
    "enabled": true,
    "endpoint": "https://ingest.<region>.signoz.cloud:443",
    "protocol": "http/protobuf",
    "headers": {
      "signoz-ingestion-key": "<YOUR_SIGNOZ_INGESTION_KEY>"
    },
    "serviceName": "openclaw-gateway",
    "traces": true,
    "metrics": true,
    "logs": true,
    "sampleRate": 1,
    "flushIntervalMs": 5000
  }
}

OR you can check your ~/.openclaw/openclaw.json config file too.

Step 4: Restart your OpenClaw gateway

openclaw gateway restart

View OpenClaw Traces and Metrics in SigNoz

Once configured, OpenClaw automatically emits traces, logs, and metrics for every LLM request.

OpenClaw traces are available in SigNoz under the Traces tab:

OpenClaw traces in SigNoz showing LLM application activity — *OpenClaw traces in SigNoz: monitor LLM application spans*

When you click on a trace in SigNoz, you'll see a detailed view of the trace, including all associated spans, along with their events and attributes.

OpenClaw detailed trace view in SigNoz with spans, events, and attributes — *OpenClaw detailed trace in SigNoz: spans, events, and attributes per LLM request*

OpenClaw metrics are available in SigNoz under the Metrics tab:

OpenClaw metrics in SigNoz showing LLM usage and performance data — *OpenClaw metrics in SigNoz: track LLM usage, latency, and performance*

When you click on any of these metrics in SigNoz, you'll see a detailed view of the metric, including attributes:

OpenClaw detailed metric view in SigNoz with metric attributes and time series — *OpenClaw detailed metric in SigNoz: metric attributes and time series data*

Troubleshooting OpenClaw Observability

If you don't see your telemetry data:

Verify network connectivity - Ensure your application can reach SigNoz Cloud endpoints
Check ingestion key - Verify your SigNoz ingestion key is correct
Wait for data - OpenTelemetry batches data before sending, so wait 10-30 seconds after making API calls
Try a console exporter — Enable a console exporter locally to confirm that your application is generating telemetry data before it’s sent to SigNoz

OpenClaw Observability Dashboard

The OpenClaw observability dashboard gives you pre-built charts tailored for LLM usage, so you can monitor token usage, request rates, and latency out of the box.

Setup OpenTelemetry Collector (Optional)

What is the OpenTelemetry Collector?

Think of the OTel Collector as a middleman between your app and SigNoz. Instead of your application sending data directly to SigNoz, it sends everything to the Collector first, which then forwards it along.

Why use it?

Cleaning up data — Filter out noisy traces you don't care about, or remove sensitive info before it leaves your servers.
Keeping your app lightweight — Let the Collector handle batching, retries, and compression instead of your application code.
Adding context automatically — The Collector can tag your data with useful info like which Kubernetes pod or cloud region it came from.
Future flexibility — Want to send data to multiple backends later? The Collector makes that easy without changing your app.

See Switch from direct export to Collector for step-by-step instructions to convert your setup.

For more details, see Why use the OpenTelemetry Collector? and the Collector configuration guide.

Additional resources:

Set up alerts for high latency or error rates
Learn more about querying traces
Explore log correlation