NemoClaw
open-sourceThe section your link pointed to isn't on NemoClaw's page any more, so we've brought you to the top.
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
Summary
NemoClaw is an open-source reference stack, free under Apache 2.0, for running AI agents like OpenClaw, Hermes, and LangChain Deep Agents Code more safely inside NVIDIA OpenShell sandboxes. It runs as a CLI installed locally, with an onboarding wizard that handles sandbox setup, managed inference routing, network policy, and lifecycle operations, and it can also be driven through a starter prompt pasted into a coding agent such as Cursor, Claude Code, Codex, or Copilot. It is built for developers deploying always-on agents who need sandboxingsandboxingRunning code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. and credential handling done for them rather than assembled from scratch, and it sits in the category of infrastructure for running agents safely rather than the agents themselves. First committed in 2026, it already has 196 contributors and over six thousand commits in the past year, putting it firmly in active development.
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
How NemoClaw helps
Which sandbox is a given always-on agent actually running in, and is its network policy still active?
checks the OpenShell container backing that agent and reports its current sandbox and network policy state, so a session that quietly lost isolation shows up
Which of my agents are using managed inference versus calling a provider directly?
reports the inference route configured for each agent so a session bypassing the managed path is visible before it runs up a bill or leaks a key
How do I let a teammate choose which agent framework to run without them touching a terminal?
walks them through the same onboarding wizard one question at a time, applying their choice of OpenClaw, Hermes, or Deep Agents Code to a new sandbox
How do I hand an agent a credential without pasting it into a chat window?
routes it through a checked-in local credential helper that only fires after the exact command receiving it is shown and approved
What state was a sandbox left in the last time it ran?
restores from its last snapshot and reports what changed, so a stopped agent can resume without rebuilding its environment by hand
Languages
Release-note detail over time
See how much detail NemoClaw puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Checking release-note history…
Releases
2 entries
No entries match these filters.
- August 20262
Articles
3 articles · updated Nov 4, 2026Where NemoClaw turns up in what others publish: how-tos, attack reports that name it, and incident write-ups. A row says why it is here and quotes where the article names it; the link goes to the publisher.
-
Tutorial: Deploy NVIDIA's NemoClaw in One Click
This article was originally written by Amit Jotwani (Staff Developer Advocate at DigitalOcean) Key Takeaways NemoClaw is an open-source stack from NVIDIA designed to help developers run OpenClaw securely.
2 more quotes
DigitalOcean offers NemoClaw 1-Click Droplets that enable you to set up this stack on a CPU-optimized virtual machine and run NemoClaw.
This tutorial illustrates how to SSH into your Droplet, configure inference settings and policies, connect to NemoClaw, and effectively reconnect after the initial setup.
-
A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw
Oasis Security's head of research, Elad Luz, told The Hacker News that NemoClaw v0.0.35 fixed the issue on macOS and Linux.
2 more quotes
NemoClaw is NVIDIA's open source reference stack for running agents such as OpenClaw inside its OpenShell sandboxes, and Ollama is one of its supported local inference backends.
The report describes NemoClaw starting Ollama with OLLAMA_HOST=0.0.0.0:11434 , binding the model server to every network interface, and says the resulting API access allows an attacker to modify the model's chat…
-
Finding Nemo(Claw): Networking Issue Allows for LLM Poisoning in OpenClaw
Researchers from Cyera's Oasis Identity Research discovered the network configuration issue in Nvidia NemoClaw , and, more specifically, its Ollama API, according to a report published today.
2 more quotes
NemoClaw is a tool used to deploy the open source OpenClaw AI agent framework inside Nvidia OpenShell sandboxes, while Ollama is a popular open source runtime for running LLMs on local hardware.
In NemoClaw, the API provides the tool with local model inference through an HTTP API on port 11434.
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.
Choose a badge style and copy the code →