Quick Start

Get Started in Just 3 Simple Steps!

Zymtrace is shipped with a free perpetual trial license — use it at no cost. To profile GPUs, get a free trial GPU license.

Kubernetes (Helm)

Step 1: Add the Zymtrace Helm repository

Helm Chart Source

The Helm chart source code is available on GitHub: zystem-io/zymtrace-charts

To get started, add the Zymtrace Helm repository by running the following command:

helm repo add zymtrace https://helm.zystem.io

To verify and list available charts and versions, use:

helm search repo zymtrace --versions

Step 2: Install the backend components

Deploy the backend components using Helm:

helm upgrade --install backend zymtrace/backend \
  --namespace zymtrace \
  --create-namespace \
  --reset-then-reuse-values \
  --debug \
  --atomic

Step 3: Install the profiler as a DaemonSet

tip

The collection-agent arg should point to the gateway service or ingress, if you exposed it.

Deploy the profiler as a DaemonSet using the following command:

GPU Profiling enabled:

helm install profiler zymtrace/profiler \
  --namespace zymtrace \
  --create-namespace \
  --set profiler.cudaProfiler.enabled=true \
  --set profiler.args[0]="--collection-agent=zymtrace-gateway.zymtrace.svc.cluster.local:80" \
  --set profiler.args[1]="--disable-tls"

Note: For NVIDIA GPU metrics, the profiler needs to locate the NVML library: add --nvml-auto-scan to the profiler args to detect it automatically, or --nvml-path=/path/to/libnvidia-ml.so if you know the exact path.

For a step-by-step guide to GPU profiling on NVIDIA and AMD with Binary, Docker, or Kubernetes, see the GPU Profiler Quick Start. For advanced configuration, see Profiling CUDA Applications and AMD GPU Metrics & Profiles.

For CPU Profiling only:

helm install profiler zymtrace/profiler \
  --namespace zymtrace \
  --create-namespace \
  --debug \
  --set profiler.args[0]="--collection-agent=zymtrace-gateway.zymtrace.svc.cluster.local:80" \
  --set profiler.args[1]="--disable-tls"

We also have arm64 and x86/amd64 binary distributions of the Zymtrace profiler.

Docker Compose

Step 1: Create directory and download Docker Compose file

Create a project directory and download the Zymtrace Docker Compose configuration:

mkdir Zymtrace && cd Zymtrace
curl -LO https://dl.zystem.io/zymtrace/26.10.3/noarch/docker-compose.yml

Step 2: Start the backend services

Launch all backend services with Docker Compose:

docker compose up -d --remove-orphans

This will start:

• ClickHouse database
• PostgreSQL database
• MinIO object storage
• Zymtrace backend services (gateway, ingest, symdb, identity, ui, worker)

License Key (Optional)

If you're using a licensed version, create a .env file with your license key. This is not required for the free trial version.

echo 'ZYMTRACE_LICENSE_KEY="paste-key-here"' > .env

Replace paste-key-here with your actual license key.

Step 3: Access the UI

Navigate to http://localhost:8080 to access the Zymtrace interface.

For profiler installation with Docker, refer to the profiler installation guide.

AI Agent

Let your AI coding assistant install Zymtrace with the Zymtrace AI Agent Skills. Describe what you want in plain English; the assistant runs the right workflow and confirms each change with you.

Step 1: Install the Zymtrace skills

Claude Code

claude plugin marketplace add zystem-io/zymtrace-skills
claude plugin install zymtrace@zymtrace-skills

OpenAI Codex

codex plugin marketplace add zystem-io/zymtrace-skills

Then run /plugins in Codex and install Zymtrace from the marketplace.

Cursor

In Dashboard → Settings → Plugins, under Team Marketplaces, click Import and paste https://github.com/zystem-io/zymtrace-skills. See Install the plugin for the full steps and other tools.

Step 2: Ask it to install the backend and the profiler

Install the Zymtrace backend on my Kubernetes cluster with Helm, then install the profiler as a DaemonSet with GPU profiling enabled.

The install-zymtrace-backend skill deploys the backend with Helm or Docker Compose, including the license, databases, and air-gapped registries. The install-zymtrace-profiler skill installs the profiler on Kubernetes, Docker, or bare metal, with CPU and CUDA GPU profiling.

Step 3: Connect it to Zymtrace and start optimizing

Connect to the Zymtrace MCP server, then rank my GPU workloads by wasted GPU time and apply the highest-ROI fix.

The configure-zymtrace-mcp skill connects your assistant to the MCP server on your gateway, and the optimize-* skills find the bottleneck and apply the fix in your source.

Start Using Zymtrace: Efficiency IQ

Once deployed, access the Efficiency IQ page for a high-level overview of your fleet's performance. From this view, you can quickly spot performance spikes and identify emerging usage patterns, allowing you to optimize your system effectively. You can also navigate to flamegraphs and functions page from the Efficiency IQ dashboard.

You're all set!

---

📐 Architecture

Learn about Zymtrace's architecture and components

Learn More

✨ Install Zymtrace Backend

Deploy Zymtrace backend

Learn More

⚡ Install Zymtrace Profiler

Install Zymtrace agent with Helm, Kubernetes manifests, Docker...

Learn More