Introduction
NVIDIA NemoClaw for LangChain Deep Agents Code runs LangChain Deep Agents Code inside an OpenShell sandbox. Thenemo-deepagents command is the Deep Agents-focused alias for NemoClaw.
The NemoClaw Deep Agents blueprint brings together LangChain Deep Agents Code, NVIDIA Nemotron 3 Ultra, and the NVIDIA OpenShell runtime so teams can run coding agents with controlled tools, runtime policy, observability, and model routing.
Tavily can be enabled for a nemo-deepagents sandbox by applying NemoClaw’s tavily policy preset and registering a tavily-search credential with the OpenShell gateway. The raw Tavily API key stays on the host gateway; it should not be written into the sandbox, project .env files, or Deep Agents config files.
Prerequisites
- Docker is installed and running.
- NemoClaw is installed with the LangChain Deep Agents Code agent available.
- You have a Tavily API key from the Tavily Dashboard.
Setup
Step 1: Install or onboard Nemo Deep Agents
Step 1: Install or onboard Nemo Deep Agents
If NemoClaw is not installed yet, select the LangChain Deep Agents Code agent before running the installer:If NemoClaw is already installed, start Deep Agents onboarding directly:During onboarding, choose your inference provider, model, sandbox name, and policy tier. The walkthrough uses
dcode-tavily as the sandbox name:Step 2: Review the sandbox policy presets
Step 2: Review the sandbox policy presets
List the active and available policy presets for the sandbox:Preview the exact egress changes the Tavily preset will apply:
Step 3: Apply the Tavily policy preset
Step 3: Apply the Tavily policy preset
Apply the maintained This opens managed Python egress for Tavily search and extract requests to
tavily preset to the target sandbox:api.tavily.com.Step 4: Register the Tavily credential with the gateway
Step 4: Register the Tavily credential with the gateway
Export your key only in the host shell long enough for NemoClaw to register it:If you need to replace an existing credential, reset it first:
Step 5: Rebuild the sandbox
Step 5: Rebuild the sandbox
Rebuild the sandbox so the new policy and gateway provider attach to the runtime:The rebuild should restore the existing workspace state, reapply the policy presets, and restart LangChain Deep Agents Code.
Step 6: Connect and test web search
Step 6: Connect and test web search
Open the Deep Agents Code terminal:Ask a current-events question, for example:When Deep Agents requests a web-search action, review the tool call and approve it if the query is appropriate.
How Tavily works in Nemo Deep Agents
| Layer | What it does |
|---|---|
tavily policy preset | Opens the sandbox Python egress path for Tavily search and extract API calls. |
tavily-search gateway credential | Stores the Tavily API key on the OpenShell host gateway and injects it at egress time. |
| Sandbox rebuild | Attaches the updated policy and credential provider to the sandbox runtime. |
| Deep Agents approval | Lets you review tool calls before the coding agent performs web search. |
Good tasks for Nemo Deep Agents + Tavily
- researching current package, API, and framework behavior before editing code
- reading and summarizing live documentation during a coding task
- checking recent release notes, issues, or changelogs
- grounding implementation choices in current source material
- extracting clean content from URLs the agent needs to inspect
Troubleshooting
| Symptom | What to check |
|---|---|
| Web search cannot reach Tavily | Run nemo-deepagents dcode-tavily policy-list and confirm tavily is active. |
| The key is not being used | Re-register tavily-search, then rebuild the sandbox. |