Nvidia has officially rolled out a range of open-source features, particularly designed to offer excellent capabilities of artificial intelligence (AI)-centric agents during annual GTC developer conference.
Nvidia’s first new tool, NemoClaw, enhances the safety and output quality of OpenClaw community.
What is OpenClaw?
OpenClaw is a famous open-source AI agent that can run on everyone’s personal computers, and capable of automating multistep tasks, including organizing locally stored files and performing online research.
NemoClaw comprises multiple components such as OpenShell, a tool that improves privacy and cybersecurity guardrails to OpenClaw. It does so by running OpenClaw in a sandbox that prevents it from accessing files not necessary to the tasks it performs. The tool also limits the agent’s network access.
As per Nvidia, it’s also possible to incorporate agents with cloud-hosted large language models.
With the latest tool, users are now allowed to download both OpenShell and Nemotron with a single command, as NemoClaw is able to power other AI-centric agents that use their own models from providers, including OpenAI Group PBC and Anthropic PBC.
Nvidia CEOJensen Huang, “Employees will be supercharged by teams of frontier, specialized and custom-built agents they deploy and manage. The enterprise software industry will evolve into specialized agentic platforms, and the IT industry is on the brink of its next great expansion.”
NemoClaw utilizes NVIDIA Agent Toolkit software to optimize OpenClaw in a single command.
Agent Toolkit allows developers to create custom AI agents that automate multi-step tasks.
OpenShell and Nemotron, the two core components of NemoClaw, also ship with another open-source project that Nvidia launched.
It is pertinent to mention, Nvidia is currently planning to join forces with some companies to integrate Agent Toolkit with their products. Adobe Inc., IBM Corp.’s Red Hat unit, Box Inc. and Cadence Design Systems Inc. are among the early adopters.
