Gradient, an AI R&D lab, has open-sourced Parallax, a new operating system designed for sovereign AI. This platform enables individuals and teams to build, host, and access powerful AI applications on their own devices and private networks, reducing reliance on centralized cloud infrastructure. Parallax turns everyday hardware like laptops and desktops into an adaptive network that functions as a single, high-performance computer, allowing for private and efficient AI execution.
Gradient open-sources Parallax, a sovereign AI operating system.
The OS lets users run AI models on their own devices and private networks.
It turns multiple devices into one adaptive, high-performance compute network.
Parallax supports over 40 open models on Windows, macOS, and Linux.
It demonstrated up to 3.6x higher throughput in tests versus other local frameworks.
The goal is to enable "owned intelligence" versus "rented" cloud-based AI.
Parallax is engineered to make advanced AI infrastructure accessible and private. It allows large AI models that typically require expensive cloud servers to run collaboratively across a user's own hardware. The system automatically splits and routes workloads for maximum speed and efficiency, keeping all data and memory local. This ensures privacy, verifiability, and reproducibility, as every step of computation can be tracked and audited. “Parallax is the easiest way to host your own agents and applications - privately, efficiently, and without relying on the cloud,” said Eric Yang, Founder and CEO of Gradient.
The launch is positioned as a significant shift in the AI industry, moving away from a model of increasingly large, centralized cloud services towards open, user-controlled systems. The company describes this as a transition from "rented intelligence to owned intelligence." Backed by investors like Pantera and Multicoin, Gradient aims to build the backbone for a sovereign AI ecosystem. “The release of Parallax marks a turning point for the AI industry. For years, progress has meant bigger models and bigger clouds. Sovereign AI is the next phase: open systems that anyone can run, verify, and improve," Yang stated.
With the release of Parallax and its underlying research, Gradient is pushing the frontier of decentralized AI. By providing an open-source OS that leverages existing hardware, the company is empowering developers and researchers to build, host, and evolve AI applications on their own terms, fostering a more accessible and verifiable future for artificial intelligence.
About Gradient
Gradient is an AI R&D lab dedicated to building open intelligence through a fully decentralized infrastructure - OIS (Open Intelligence Stack), encompassing distributed training, serving, agentic systems, and more.
We are solving the hardest and most ambitious problem in the intersection of Blockchain x AI: How do we train/serve good LLMs over the public internet - Is it even possible to build an OpenAI competitor over a permissionless, autonomous network? Our current OIS includes Parallax for distributed serving, Echo for distributed reinforcement learning, and Gradient Cloud for enterprise solutions.
Backed by top investors and a team of world-class researchers, Gradient is committed to releasing more frontier research that will unlock a future where intelligence can be assembled, scaled, and evolved by anyone, anywhere.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.