shipfeedAI news, curated daily

02:03:28 CET
21 MAY02:03:28shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Run untrusted code with Vercel Sandbox, now generally available

Vercel Sandbox launches as generally available, offering isolated microVM execution environments for AI agents, alongside open-sourcing the CLI and SDK for community use.

Jan 30 · · primary fetch1 sourceupdated Jan 30 ·

AI agents are changing how software gets built. They clone repos, install dependencies, run tests, and iterate in seconds. Despite the change in software, most infrastructure was built for humans, not agents. Traditional compute assumes someone is in the loop, with minutes to provision and configure environments. Agents need secure, isolated environments that start fast, run untrusted code, and disappear when the task is done. Today, Vercel Sandbox is generally available, the execution layer for agents, and we're open-sourcing the Vercel Sandbox and for the community to build on this infrastructure.CLISDK Vercel processes over 2.7 million deployments per day.

Each one spins up an isolated microVM, runs user code, and disappears, often in seconds. To do that at scale, we built our own compute platform. Internally code-named Hive, it’s powered by and orchestrates microVM clusters across multiple regions. When you click Deploy in , import a repo, clone a template, or run in the CLI, Hive is what makes it feel quick.Firecrackerv0vercel Sandbox brings that same infrastructure to agents. Agents don’t work like humans. They spin up environments, execute code, tear them down, and repeat…

read full article on vercel.com
§ sources1 publication · timeline below
  1. vercel.comRun untrusted code with Vercel Sandbox, now generally availableprimary