NVIDIA NemoClaw: the open-source AI agent platform, explained

NVIDIA NemoClaw is the open-source reference stack NVIDIA ships for running supported agents safely on its own hardware. Kortix is the open-source AI Management System for a whole agent workforce, on any infrastructure, with your keys. NemoClaw governs how an agent executes; Kortix governs how finished work lands. The choice turns on which layer your team actually needs.

What NemoClaw is

NVIDIA NemoClaw is an open-source reference stack for running supported AI agents more safely inside NVIDIA OpenShell sandboxes (GitHub). It ships as a collection of blueprints that bundle three pieces of the NVIDIA Agent Toolkit: Nemotron and other frontier models, NeMo for specialization and optimization, and OpenShell for runtime policy controls. The blueprints move a team from prototype to governed deployment with runtime controls, model routing, skill execution, and observability (overview).

The stack supports three agents: OpenClaw as the default, Hermes, and LangChain Deep Agents Code (GitHub). OpenClaw, the default agent, was first called Clawdbot, then Moltbot, before OpenAI acquired the project (WIRED).

NemoClaw ships under Apache 2.0, and NVIDIA labels it an alpha project. It is a stack you run and extend yourself. There is no managed offering and no support SLA.

What NemoClaw does best

NemoClaw gives a single agent a governed place to run, which is what teams adopting agents on local hardware need most.

• Sandboxed execution. OpenShell is the security boundary and enforces what the agent can access: files, networks, credentials, and tools.
• Policy controls. Network rules, an operator approval flow, egress control, and sandbox hardening keep sensitive actions under review.
• Managed inference. You choose local Nemotron models, cloud frontier models, or a router that blends both under privacy controls.
• Lifecycle operations. The NemoClaw CLI covers guided onboarding, snapshots, and agent aliases for each supported harness.
• Hardware fit. NVIDIA provides local, 24/7 compute on RTX Spark laptops, GeForce RTX PCs and laptops, RTX PRO workstations, and DGX Station or DGX Spark (overview).

NVIDIA also continues to contribute to OpenClaw, the project its default agent comes from (overview). For a team already using NVIDIA hardware, that is one supported path from a laptop or workstation to an always-on agent.

How NemoClaw runs an agent

NemoClaw installs with one shell command: curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash. That command defaults to OpenClaw. Set the NEMOCLAW_AGENT variable to hermes or langchain-deepagents-code to run Hermes or LangChain Deep Agents Code instead (overview).

Whichever agent you choose runs inside an OpenShell sandbox. OpenShell is the runtime that enforces what the agent can access, and it applies network policy and managed inference under operator approval. The express install path takes the recommended preset and installs OpenClaw by default; choosing otherwise lets you pick the agent, a sandbox name, an inference provider, and a model interactively. NemoClaw wraps that runtime with the CLI and its agent-specific aliases (GitHub).

NemoClaw is hardware-centric. NVIDIA lists local compute on RTX Spark laptops, GeForce RTX PCs and laptops, RTX PRO workstations, and DGX Station or DGX Spark. The repository requires a supported DGX or Windows Subsystem for Linux host. Alpha status matters here: maintainers review issues, discussions, and pull requests on a best-effort basis, with no guaranteed response timelines (overview, GitHub).

Where NemoClaw stops and Kortix starts

NemoClaw governs how an agent executes. Kortix governs how finished work lands. Kortix keeps your agents, skills, company memory, and connectors in one git repo you own. Each session runs an agent in an isolated sandbox on its own branch. When the work is ready, the agent opens a change request, and a person reviews and merges it to the default branch (Kortix docs).

The guardrails sit at different points. In NemoClaw, OpenShell constrains the agent while it runs. In Kortix, the review step constrains what reaches production: only commits a person merges survive. That difference matters most when many agents work at once and every change needs an owner.

Kortix is model-agnostic. You run any model with your own keys, in the cloud or on your own hardware. Kortix is open source (Elastic License 2.0): self-host, read and modify the code.

The repo also holds your connectors: 3,000+ apps plus any MCP or API, with credentials brokered server-side so they never enter the agent's machine. The same repo carries the configuration: the machine image sessions boot, the rules each agent may touch, and the triggers that start work (Kortix).

Each session boots its own isolated Linux machine, and thousands run in parallel with no crossover between them. You start those sessions from the web app, Slack, Teams, email, mobile, the CLI, or the API, or from cron schedules and signed webhooks with nobody asking.

Side by side

Both projects are open source and both run the agent inside a sandbox. The differences that decide a pick are where it runs and how its work gets approved.

When to pick which

Pick NemoClaw if your team already runs supported NVIDIA hardware and wants an always-on agent under policy controls. It gives that agent a sandboxed, governed place to execute, with OpenShell enforcing its file, network, credential, and tool access, and a CLI to manage its lifecycle. The trade is real: NemoClaw is alpha software tied to NVIDIA hosts, and it governs execution. Landing the finished work is a separate layer (GitHub).

Pick Kortix when you want to manage many agents across any infrastructure with a human gate on every change. Your agents, skills, company memory, and connectors live in one git repo you own. Each session runs in its own isolated sandbox, and its work reaches the default branch only when a person merges the change request. That model scales past a single always-on assistant. Every agent draws on the same company memory, and a single review gate covers the whole fleet. Any model, your keys, self-hosted or managed cloud (Kortix docs).

For a wider view of the category, read the guide to open-source AI agent platforms and the roundup of open-source Claude Cowork alternatives.

Get started with open-source Kortix: start free, then self-host on your own infrastructure.