Zettar offers zx, a scale‑out data‑mover that automates high‑speed transfers of petabyte‑scale datasets across on‑prem, edge and cloud storage, supporting both POSIX file systems and S3‑compatible object stores. Its peer‑to‑peer architecture distributes workload across multiple Linux servers or DPUs, delivering linear throughput scaling and secure, checksum‑verified transfers via TLS and RESTful APIs.
Funding
$225K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Enterprises that generate petabyte‑scale data—such as AI training sets, genomics pipelines, oil‑field imaging, or autonomous‑vehicle sensor streams—must move that data between edge sites, on‑premises storage, private clouds, and public clouds. Existing tools are often single‑node, protocol‑specific, and unable to fully utilize available network bandwidth, leading to long transfer times, high operational costs, and vendor lock‑in.
Solution
Zettar delivers zx, a unified, scale‑out data‑mover software that orchestrates high‑speed transfers across any combination of file‑based or object‑based storage, regardless of location. The peer‑to‑peer architecture distributes workload across multiple nodes, automatically exploiting storage, CPU, memory, and network capacity to achieve petascale throughput. zx supports both bulk copy of existing datasets and append‑streaming of live, fast‑growing data, with built‑in TLS encryption, end‑to‑end checksumming, and incremental synchronization. Management is available through an intuitive web UI or programmatically via RESTful APIs and SDKs, enabling automation and integration into existing data pipelines. The solution runs on standard x86_64 or aarch64 Linux servers and can be embedded in DPUs/IPUs, providing flexibility across on‑prem, edge, and cloud environments while eliminating vendor lock‑in.
Target Audience
Primary customers are large‑scale data‑intensive organizations—such as HPC centers, AI/ML research labs, life‑science genomics facilities, oil & gas exploration firms, media & entertainment studios, and autonomous‑vehicle fleets—that require fast, reliable, and cost‑effective movement of petabyte‑level datasets across hybrid‑cloud infrastructures.
Features
- Unified zx platform integrates four modules (zx‑File, zx‑Object, zx‑Single‑Site‑Copy, zx‑Append‑Streaming) under a single management console.
- Peer‑to‑peer scale‑out architecture delivers linear performance scaling; a single node can sustain >70 Gbps, and multi‑node clusters exceed 100 Gbps.
- Supports both POSIX file systems and S3‑compatible object stores, enabling transparent file‑to‑object tiering and migration.
- Append‑streaming capability handles live data rates up to 800 Gbps, suitable for high‑speed instruments and sensor fleets.
- RESTful API and SDK provide full automation, job scheduling, and integration with CI/CD pipelines.
- TLS encryption, per‑transfer checksum verification, and role‑based access control ensure data integrity and security.
- Multi‑tenant design allows multiple users to run isolated transfers on the same cluster with exclusive data areas.
- Hardware‑agnostic deployment on bare metal, virtual machines, containers, or DPUs/IPUs across on‑prem, edge, and public cloud environments.