Nemo Deep Agents

Enable Tavily for NVIDIA NemoClaw’s nemo-deepagents sandbox so LangChain Deep Agents Code can use web search and extraction through governed OpenShell egress.

Introduction

NVIDIA NemoClaw for LangChain Deep Agents Code runs LangChain Deep Agents Code inside an OpenShell sandbox. The nemo-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.

NemoClaw treats Tavily as an explicit sandbox egress opt-in. Registering the credential alone is not enough; the target sandbox also needs the tavily policy preset.

Setup

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:

export NEMOCLAW_AGENT=langchain-deepagents-code
curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

If NemoClaw is already installed, start Deep Agents onboarding directly:

nemo-deepagents onboard

During onboarding, choose your inference provider, model, sandbox name, and policy tier. The walkthrough uses dcode-tavily as the sandbox name:

nemo-deepagents dcode-tavily status

Step 2: Review the sandbox policy presets

List the active and available policy presets for the sandbox:

nemo-deepagents dcode-tavily policy-list

Preview the exact egress changes the Tavily preset will apply:

nemo-deepagents dcode-tavily policy-add tavily --dry-run

Step 3: Apply the Tavily policy preset

Apply the maintained tavily preset to the target sandbox:

nemo-deepagents dcode-tavily policy-add tavily --yes

This opens managed Python egress for Tavily search and extract requests to api.tavily.com.

Step 4: Register the Tavily credential with the gateway

Export your key only in the host shell long enough for NemoClaw to register it:

export TAVILY_API_KEY="tvly-YOUR_API_KEY"
nemo-deepagents credentials add tavily-search --type tavily --credential TAVILY_API_KEY
unset TAVILY_API_KEY

If you need to replace an existing credential, reset it first:

nemo-deepagents credentials reset tavily-search

Step 5: Rebuild the sandbox

Rebuild the sandbox so the new policy and gateway provider attach to the runtime:

nemo-deepagents dcode-tavily rebuild

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

Open the Deep Agents Code terminal:

nemo-deepagents dcode-tavily connect

Ask a current-events question, for example:

What is the latest news on AI?

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.

Do not place TAVILY_API_KEY in the sandbox, project .env files, /sandbox/.deepagents, or Deep Agents config. NemoClaw’s managed gateway is designed to keep the raw key outside the sandbox.

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.

Learn more

• LangChain and NVIDIA NemoClaw Deep Agents blueprint announcement
• NVIDIA NemoClaw Deep Agents quickstart
• Tavily Search API
• Tavily Extract API