Local Healthcare Agent on DGX Station

IMPORTANT

This playbook requires Docker (with NVIDIA runtime), Node.js v22, and OpenShell CLI >= 0.0.33. If Docker, the NVIDIA runtime, or OpenShell are missing, complete the NemoClaw playbook (nvidia/station-nemoclaw/instructions.md) Steps 1–4 first — that takes about 30–45 minutes. Ollama runs as a Docker container in this playbook (host Ollama is not required and will conflict with port 11434, see Step 3).

NOTE

Steps 1–3 are prerequisites. Steps 4–5 configure infrastructure and deploy the agent. Steps 6–9 are the demo. Steps 10–11 are cleanup and next steps.

Step 1
Verify your environment

Confirm your DGX Station has the required software and free disk space:

# OpenShell installs to ~/.local/bin, which is not on the default
# non-interactive PATH. Add it before running anything below.
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
export PATH="$HOME/.local/bin:$PATH"

nvidia-smi
docker info --format '{{.ServerVersion}}'
node --version
ollama --version 2>/dev/null || echo "ollama not installed (OK — Docker provides it)"
openshell --version
df -h /

Expected: Blackwell Ultra GPU, Docker >= 23.0.1, Node.js v22.x (the DGX Station ships with v18 — see below), OpenShell >= 0.0.33, and at least 200 GB free on / (86 GB model + Docker images + working space).

WARNING

If openshell --version says command not found, the binary is at ~/.local/bin/openshell but isn't on PATH. Run the export PATH=... line above and re-source ~/.bashrc. Without this, every openshell and make command in later steps fails.

TIP

make prereq (run from ~/clinical-intelligence after Step 2) bundles all of the checks below — Docker, Node version, OpenShell, disk space, GPU, port 11434, and NGC auth — into one command.

If node --version reports v18.x or older, install Node.js v22 before continuing:

curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
node --version   # should now show v22.x

Host Ollama must not be on port 11434. This playbook runs Ollama in a Docker container that binds 11434 on the host. Run both of these:

# Always run — succeeds silently if no service exists, stops the host
# Ollama daemon if NemoClaw or another playbook left one running.
sudo systemctl stop ollama 2>/dev/null || true
sudo systemctl disable ollama 2>/dev/null || true

# Verify nothing else owns 11434.
ss -tlnp 2>/dev/null | grep 11434 || echo 'port 11434 free'

Expected: port 11434 free. If the line still shows a listener, something else (an old ollama serve, another container, etc.) owns the port — stop it, or change OLLAMA_PORT in .env (Step 2) to a free port such as 11435. make setup sources .env and configures the sandbox provider against the override.

Stale OpenShell gateway? If you previously ran the NemoClaw playbook, an existing gateway will be silently reused under the new name. To start clean:

openshell gateway destroy 2>/dev/null || true

Step 2
Copy the assets and configure

The playbook assets include the Docker Compose file, agent definitions, skill files, and setup scripts. Locate the assets/ directory shipped with this playbook (DGX Station catalog or your local clone) and copy it to ~/clinical-intelligence:

# Find the playbook directory first. Try the common locations:
PLAYBOOK_DIR=""
for d in ~/dgx-station-playbooks/nvidia/station-healthcare-agent \
         /opt/dgx-station-playbooks/nvidia/station-healthcare-agent \
         /usr/local/share/dgx-station-playbooks/nvidia/station-healthcare-agent; do
  if [ -d "$d/assets" ]; then PLAYBOOK_DIR="$d"; break; fi
done

if [ -z "$PLAYBOOK_DIR" ]; then
  echo "ERROR: assets/ not found. Locate it manually:"
  echo "  find / -type d -path '*station-healthcare-agent/assets' 2>/dev/null"
  echo "Then re-run with PLAYBOOK_DIR set."
else
  cp -r "$PLAYBOOK_DIR/assets" ~/clinical-intelligence
  cd ~/clinical-intelligence
  cp .env.example .env
  nano .env
  # Set: NGC_API_KEY=nvapi-...
fi

IMPORTANT

If the catalog tarball did not include assets/ (some early distributions stripped it), pull the playbook directly from the repo:

git clone https://github.com/NVIDIA/dgx-station-playbooks ~/dgx-station-playbooks
cp -r ~/dgx-station-playbooks/nvidia/station-healthcare-agent/assets ~/clinical-intelligence

The NGC API key is required to download the OpenFold3 NIM image from nvcr.io and to run it at runtime. Get one for free at ngc.nvidia.com.

Authenticate Docker against NGC so the OpenFold3 image pull succeeds (without this you get a raw HTML 401 from nginx):

make ngc-login
# or, equivalent manual command:
# echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

Step 3
Start Nemotron 3 Super and OpenFold3

Ollama serves Nemotron 3 Super for LLM inference. OpenFold3 NIM handles protein structure prediction. Both run as Docker containers with GPU access.

If you are connected via SSH, start a tmux or screen session first so the download survives a disconnection:

tmux new -s clinical

Start the services:

docker compose up -d ollama openfold3

NOTE

First run downloads Nemotron 3 Super (~86 GB). This takes 15–25 minutes on a fast connection, up to an hour on slower links. Monitor with docker compose logs -f ollama. If interrupted, re-run — it resumes where it left off.

TIP

Multi-GPU stations: docker-compose pins both Ollama and OpenFold3 to GPU 0 by default (set LLM_GPU and OPENFOLD_GPU in .env to override). On the dual-GPU DGX Station (RTX PRO 6000 + GB300), set LLM_GPU and OPENFOLD_GPU to the index of the GB300 because Nemotron-3-Super (~94 GB resident) does not fit safely on the RTX PRO 6000 (98 GB). Find the GB300 index with: nvidia-smi --query-gpu=index,name --format=csv,noheader | awk -F', ' '/GB300/{print $1; exit}'

Pull the model into Ollama:

docker compose up model-pull

Wait for all services to report healthy:

make status

Expected:

  Ollama:    ✓ healthy
  OpenFold3: ✓ healthy

OpenFold3 takes ~3 minutes to load model weights on startup. If it shows "down (may still be loading)", wait and check again.

TIP

make up runs all of the above (container start + model pull) in one command but does not block on health. Run make status separately to verify services are healthy.

Step 4
Start the OpenShell gateway

The OpenShell gateway runs a lightweight k3s Kubernetes cluster inside Docker to manage sandboxes. On DGX Station, the kernel uses cgroup v2 with the systemd driver, but k3s defaults to cgroupfs. The flag below tells k3s to match the host:

OPENSHELL_K3S_ARGS='--kubelet-arg=cgroup-driver=systemd' openshell gateway start

Wait for the gateway's embedded k3s cluster to finish initializing (10–15 seconds after gateway start returns), then verify:

# Wait until the gateway accepts connections, fail after 60s
for i in $(seq 1 30); do
    if openshell status 2>/dev/null | grep -q "Connected"; then
        echo "Gateway: Connected"; break
    fi
    sleep 2
done
openshell status

Expected: Status: Connected. If the first openshell status immediately after gateway start reports Connection reset by peer, that is normal — k3s is still warming up. The loop above polls until it is ready.

NOTE

Step 4 configures OpenShell infrastructure (gateway). Step 5 deploys the healthcare agent into this infrastructure.

Step 5
Deploy the healthcare agent

make setup automates six operations:

Creates the clinical-sandbox OpenShell sandbox with the network policy from sandbox-policy.yaml
Creates the inference provider and configures routing to Ollama (previously a manual step)
Installs Python packages (requests, pandas, matplotlib) inside the sandbox
Copies agent definitions from agents/ and skill files from skills/ into the sandbox workspace
Deploys the OpenClaw configuration (openclaw.json, IDENTITY.md) and registers specialist agents
Starts the OpenClaw gateway and runs a smoke test

make setup

When complete, you will see === Setup Complete ===. If setup fails, re-run make setup — it recreates the sandbox from scratch, so all config is fresh.

Verify the sandbox config matches the repo:

make check

All checks should pass. If any skills or config files are stale, make check tells you what to fix.

Run the quick test suite:

make test

TIP

make setup runs bash scripts/setup_sandbox.sh (loopback bind — use the SSH tunnel from Step 6 for remote browsers). For direct local-browser access on the Station itself, run make setup-local instead, which calls bash scripts/setup_sandbox.sh --local. See RUNBOOK.md in the assets for the manual step-by-step equivalent.

Step 6
Open the dashboard

Remote access (run this from your machine, not the DGX Station). This forwards port 18789 so you can open the dashboard in a local browser:

ssh -f -N -L 18789:localhost:18789 your-user@your-dgx-station-ip

Cursor / VS Code: Open the Ports tab in the bottom panel, click Forward a Port, enter 18789.

Then open http://localhost:18789/ in your browser.

Local (keyboard and monitor on Station): Open http://localhost:18789/.

You should see the OpenClaw dashboard with Health: OK. Click Chat.

Setup is done. The next steps are the demo.

Step 7
Run healthcare queries

All queries execute inside the OpenShell sandbox — only whitelisted endpoints are reachable. You will verify this in Step 9.

Paste the first query. The first response takes 30–60 seconds while the 120B model loads into GPU memory — this is normal and only happens once per session.

Find all diabetic patients and get their latest HbA1c. Generate a histogram with a red dashed line at 9%. Use dark background with green bars.

The agent reads its skill files (fhir-basics, clinical-knowledge, analysis-methods), imports the FHIR helpers library, writes a Python script, queries the FHIR server, and generates the chart — all inside the sandbox.

You should see ~48 diabetic patients and an A1c histogram with a 9% threshold line. The agent includes a clickable link to the chart in its response. You can also browse all visualizations at http://localhost:18789/__openclaw__/canvas/.

Stay in the same session for follow-ups:

Which of those diabetic patients also have hypertension? For the overlap, get their eGFR. Flag anyone with eGFR below 60 as kidney disease risk.

You should see ~24 with both conditions, ~12 flagged as kidney disease risk.

Of those kidney disease risk patients, which ones are not on an ACE inhibitor or ARB?

You should see ~12 patients missing guideline-recommended therapy (100% care gap in the synthetic data).

Step 8
Visualize a drug target

Show me the 3D protein structure of atorvastatin bound to its target

The molecular agent looks up atorvastatin's target protein (HMG-CoA reductase), fetches the drug's SMILES from PubChem, sends the protein sequence to OpenFold3 for structure prediction, and generates an interactive 3D viewer with confidence scores (pLDDT, pTM, ipTM).

You should see an interactive 3D viewer with the protein ribbon structure and atorvastatin ligand. The agent includes a clickable link. Confidence scores appear in the viewer header — pLDDT > 70 indicates a good prediction.

Step 9
Understand sandbox isolation

The sandbox policy (sandbox-policy.yaml) enforces implicit-deny networking at Layer 7. Every outbound connection is blocked unless an explicit rule allows it. The policy also restricts HTTP methods — FHIR and PubChem are limited to read-only (GET/HEAD), OpenFold3 accepts only POST to specific prediction paths.

Confirm that unauthorized endpoints are blocked. From inside the sandbox (connect with openshell sandbox connect clinical-sandbox), run:

curl --max-time 5 https://google.com

Expected: connection refused or CONNECT tunnel failed, response 403. The allowed endpoints are:

Endpoint	Purpose	Allowed methods
`https://inference.local` (port 443 only)	LLM calls to Ollama	All (OpenAI protocol)
`r4.smarthealthit.org`	FHIR patient data	GET, HEAD
`pubchem.ncbi.nlm.nih.gov`	Drug SMILES lookup	GET, HEAD
OpenFold3 NIM (Docker bridge)	Structure prediction	POST `/biology/openfold/*`, GET `/v1/health/`
CDN (jquery, 3dmol, unpkg)	JavaScript for 3D viewers	GET

Everything else is denied. Additional rules for GitHub, npm, and PyPI are included in sandbox-policy.yaml for build dependencies during sandbox setup — these are setup-only and not used at runtime.

NOTE

inference.local is HTTPS-only. Plain http://inference.local/... returns policy_denied because the OpenShell L7 proxy enforces the TLS-terminated CONNECT path. All skills, helper scripts, and _sandbox curls in this repo use https://inference.local with -k (the proxy presents a self-signed cert).

Patient data flows from FHIR → sandbox Python execution. It never passes through the LLM, OpenFold3, or PubChem.

Inspect a skill file to see the editable clinical knowledge:

head -30 skills/clinical-knowledge/SKILL.md

Skill files are Markdown. Edit a threshold or drug classification — it takes effect on the next query, no retraining. Try changing the HbA1c threshold from 9.0% to 7.0% and re-running the diabetes query to see the difference.

Step 10
Cleanup

WARNING

This removes the sandbox and stops all services.

openshell sandbox delete clinical-sandbox
make down
openshell gateway destroy

To also remove downloaded models and volumes:

make clean

Step 11
Next steps

Edit a skill — change a lab reference range in skills/clinical-knowledge/SKILL.md and re-run the same prompt to see the effect.
Add an agent — create a .md in agents/, register in openclaw.json, redeploy with make setup.
Connect a real FHIR server — replace the test server URL, add OAuth2 authentication, and update sandbox-policy.yaml with explicit path-level rules for the FHIR resources the agent needs.
Swap models — try qwen2.5:72b or another Ollama model by editing .env and openclaw.json.
Verify after changes — run make check after any config or skill file change to catch stale sandbox copies.
Full agent validation — make test-full runs all test levels including end-to-end agent queries (~20 min).
Monitor GPU — nvidia-smi shows memory allocation across Nemotron 3 Super and OpenFold3.

IMPORTANT

NOTE

Steps 1–3 are prerequisites. Steps 4–5 configure infrastructure and deploy the agent. Steps 6–9 are the demo. Steps 10–11 are cleanup and next steps.

Step 1
Verify your environment

Confirm your DGX Station has the required software and free disk space:

# OpenShell installs to ~/.local/bin, which is not on the default
# non-interactive PATH. Add it before running anything below.
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
export PATH="$HOME/.local/bin:$PATH"

nvidia-smi
docker info --format '{{.ServerVersion}}'
node --version
ollama --version 2>/dev/null || echo "ollama not installed (OK — Docker provides it)"
openshell --version
df -h /

WARNING

TIP

make prereq (run from ~/clinical-intelligence after Step 2) bundles all of the checks below — Docker, Node version, OpenShell, disk space, GPU, port 11434, and NGC auth — into one command.

If node --version reports v18.x or older, install Node.js v22 before continuing:

curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
node --version   # should now show v22.x

Host Ollama must not be on port 11434. This playbook runs Ollama in a Docker container that binds 11434 on the host. Run both of these:

# Always run — succeeds silently if no service exists, stops the host
# Ollama daemon if NemoClaw or another playbook left one running.
sudo systemctl stop ollama 2>/dev/null || true
sudo systemctl disable ollama 2>/dev/null || true

# Verify nothing else owns 11434.
ss -tlnp 2>/dev/null | grep 11434 || echo 'port 11434 free'

Stale OpenShell gateway? If you previously ran the NemoClaw playbook, an existing gateway will be silently reused under the new name. To start clean:

openshell gateway destroy 2>/dev/null || true

Step 2
Copy the assets and configure

# Find the playbook directory first. Try the common locations:
PLAYBOOK_DIR=""
for d in ~/dgx-station-playbooks/nvidia/station-healthcare-agent \
         /opt/dgx-station-playbooks/nvidia/station-healthcare-agent \
         /usr/local/share/dgx-station-playbooks/nvidia/station-healthcare-agent; do
  if [ -d "$d/assets" ]; then PLAYBOOK_DIR="$d"; break; fi
done

if [ -z "$PLAYBOOK_DIR" ]; then
  echo "ERROR: assets/ not found. Locate it manually:"
  echo "  find / -type d -path '*station-healthcare-agent/assets' 2>/dev/null"
  echo "Then re-run with PLAYBOOK_DIR set."
else
  cp -r "$PLAYBOOK_DIR/assets" ~/clinical-intelligence
  cd ~/clinical-intelligence
  cp .env.example .env
  nano .env
  # Set: NGC_API_KEY=nvapi-...
fi

IMPORTANT

If the catalog tarball did not include assets/ (some early distributions stripped it), pull the playbook directly from the repo:

git clone https://github.com/NVIDIA/dgx-station-playbooks ~/dgx-station-playbooks
cp -r ~/dgx-station-playbooks/nvidia/station-healthcare-agent/assets ~/clinical-intelligence

The NGC API key is required to download the OpenFold3 NIM image from nvcr.io and to run it at runtime. Get one for free at ngc.nvidia.com.

Authenticate Docker against NGC so the OpenFold3 image pull succeeds (without this you get a raw HTML 401 from nginx):

make ngc-login
# or, equivalent manual command:
# echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

Step 3
Start Nemotron 3 Super and OpenFold3

Ollama serves Nemotron 3 Super for LLM inference. OpenFold3 NIM handles protein structure prediction. Both run as Docker containers with GPU access.

If you are connected via SSH, start a tmux or screen session first so the download survives a disconnection:

tmux new -s clinical

Start the services:

docker compose up -d ollama openfold3

NOTE

TIP

Pull the model into Ollama:

docker compose up model-pull

Wait for all services to report healthy:

make status

Expected:

  Ollama:    ✓ healthy
  OpenFold3: ✓ healthy

OpenFold3 takes ~3 minutes to load model weights on startup. If it shows "down (may still be loading)", wait and check again.

TIP

make up runs all of the above (container start + model pull) in one command but does not block on health. Run make status separately to verify services are healthy.

Step 4
Start the OpenShell gateway

OPENSHELL_K3S_ARGS='--kubelet-arg=cgroup-driver=systemd' openshell gateway start

Wait for the gateway's embedded k3s cluster to finish initializing (10–15 seconds after gateway start returns), then verify:

# Wait until the gateway accepts connections, fail after 60s
for i in $(seq 1 30); do
    if openshell status 2>/dev/null | grep -q "Connected"; then
        echo "Gateway: Connected"; break
    fi
    sleep 2
done
openshell status

NOTE

Step 4 configures OpenShell infrastructure (gateway). Step 5 deploys the healthcare agent into this infrastructure.

Step 5
Deploy the healthcare agent

make setup automates six operations:

Creates the clinical-sandbox OpenShell sandbox with the network policy from sandbox-policy.yaml
Creates the inference provider and configures routing to Ollama (previously a manual step)
Installs Python packages (requests, pandas, matplotlib) inside the sandbox
Copies agent definitions from agents/ and skill files from skills/ into the sandbox workspace
Deploys the OpenClaw configuration (openclaw.json, IDENTITY.md) and registers specialist agents
Starts the OpenClaw gateway and runs a smoke test

make setup

When complete, you will see === Setup Complete ===. If setup fails, re-run make setup — it recreates the sandbox from scratch, so all config is fresh.

Verify the sandbox config matches the repo:

make check

All checks should pass. If any skills or config files are stale, make check tells you what to fix.

Run the quick test suite:

make test

TIP

Step 6
Open the dashboard

Remote access (run this from your machine, not the DGX Station). This forwards port 18789 so you can open the dashboard in a local browser:

ssh -f -N -L 18789:localhost:18789 your-user@your-dgx-station-ip

Cursor / VS Code: Open the Ports tab in the bottom panel, click Forward a Port, enter 18789.

Then open http://localhost:18789/ in your browser.

Local (keyboard and monitor on Station): Open http://localhost:18789/.

You should see the OpenClaw dashboard with Health: OK. Click Chat.

Setup is done. The next steps are the demo.

Step 7
Run healthcare queries

All queries execute inside the OpenShell sandbox — only whitelisted endpoints are reachable. You will verify this in Step 9.

Paste the first query. The first response takes 30–60 seconds while the 120B model loads into GPU memory — this is normal and only happens once per session.

Find all diabetic patients and get their latest HbA1c. Generate a histogram with a red dashed line at 9%. Use dark background with green bars.

Stay in the same session for follow-ups:

Which of those diabetic patients also have hypertension? For the overlap, get their eGFR. Flag anyone with eGFR below 60 as kidney disease risk.

You should see ~24 with both conditions, ~12 flagged as kidney disease risk.

Of those kidney disease risk patients, which ones are not on an ACE inhibitor or ARB?

You should see ~12 patients missing guideline-recommended therapy (100% care gap in the synthetic data).

Step 8
Visualize a drug target

Show me the 3D protein structure of atorvastatin bound to its target

Step 9
Understand sandbox isolation

Confirm that unauthorized endpoints are blocked. From inside the sandbox (connect with openshell sandbox connect clinical-sandbox), run:

curl --max-time 5 https://google.com

Expected: connection refused or CONNECT tunnel failed, response 403. The allowed endpoints are:

Endpoint	Purpose	Allowed methods
`https://inference.local` (port 443 only)	LLM calls to Ollama	All (OpenAI protocol)
`r4.smarthealthit.org`	FHIR patient data	GET, HEAD
`pubchem.ncbi.nlm.nih.gov`	Drug SMILES lookup	GET, HEAD
OpenFold3 NIM (Docker bridge)	Structure prediction	POST `/biology/openfold/*`, GET `/v1/health/`
CDN (jquery, 3dmol, unpkg)	JavaScript for 3D viewers	GET

NOTE

Patient data flows from FHIR → sandbox Python execution. It never passes through the LLM, OpenFold3, or PubChem.

Inspect a skill file to see the editable clinical knowledge:

head -30 skills/clinical-knowledge/SKILL.md

Step 10
Cleanup

WARNING

This removes the sandbox and stops all services.

openshell sandbox delete clinical-sandbox
make down
openshell gateway destroy

To also remove downloaded models and volumes:

make clean

Step 11
Next steps

Edit a skill — change a lab reference range in skills/clinical-knowledge/SKILL.md and re-run the same prompt to see the effect.
Add an agent — create a .md in agents/, register in openclaw.json, redeploy with make setup.
Connect a real FHIR server — replace the test server URL, add OAuth2 authentication, and update sandbox-policy.yaml with explicit path-level rules for the FHIR resources the agent needs.
Swap models — try qwen2.5:72b or another Ollama model by editing .env and openclaw.json.
Verify after changes — run make check after any config or skill file change to catch stale sandbox copies.
Full agent validation — make test-full runs all test levels including end-to-end agent queries (~20 min).
Monitor GPU — nvidia-smi shows memory allocation across Nemotron 3 Super and OpenFold3.

Local Healthcare Agent on DGX Station

Step 1
Verify your environment

Step 2
Copy the assets and configure

Step 3
Start Nemotron 3 Super and OpenFold3

Step 4
Start the OpenShell gateway

Step 5
Deploy the healthcare agent

Step 6
Open the dashboard

Step 7
Run healthcare queries

Step 8
Visualize a drug target

Step 9
Understand sandbox isolation

Step 10
Cleanup

Step 11
Next steps

Resources

Local Healthcare Agent on DGX Station

Step 1
Verify your environment

Step 2
Copy the assets and configure

Step 3
Start Nemotron 3 Super and OpenFold3

Step 4
Start the OpenShell gateway

Step 5
Deploy the healthcare agent

Step 6
Open the dashboard

Step 7
Run healthcare queries

Step 8
Visualize a drug target

Step 9
Understand sandbox isolation

Step 10
Cleanup

Step 11
Next steps

Resources

Local Healthcare Agent on DGX Station

Step 1Verify your environment

Step 2Copy the assets and configure

Step 3Start Nemotron 3 Super and OpenFold3

Step 4Start the OpenShell gateway

Step 5Deploy the healthcare agent

Step 6Open the dashboard

Step 7Run healthcare queries

Step 8Visualize a drug target

Step 9Understand sandbox isolation

Step 10Cleanup

Step 11Next steps

Resources

Local Healthcare Agent on DGX Station

Step 1Verify your environment

Step 2Copy the assets and configure

Step 3Start Nemotron 3 Super and OpenFold3

Step 4Start the OpenShell gateway

Step 5Deploy the healthcare agent

Step 6Open the dashboard

Step 7Run healthcare queries

Step 8Visualize a drug target

Step 9Understand sandbox isolation

Step 10Cleanup

Step 11Next steps

Resources

Step 1
Verify your environment

Step 2
Copy the assets and configure

Step 3
Start Nemotron 3 Super and OpenFold3

Step 4
Start the OpenShell gateway

Step 5
Deploy the healthcare agent

Step 6
Open the dashboard

Step 7
Run healthcare queries

Step 8
Visualize a drug target

Step 9
Understand sandbox isolation

Step 10
Cleanup

Step 11
Next steps

Step 1
Verify your environment

Step 2
Copy the assets and configure

Step 3
Start Nemotron 3 Super and OpenFold3

Step 4
Start the OpenShell gateway

Step 5
Deploy the healthcare agent

Step 6
Open the dashboard

Step 7
Run healthcare queries

Step 8
Visualize a drug target

Step 9
Understand sandbox isolation

Step 10
Cleanup

Step 11
Next steps