project
Vercel's sandbox service used as the deployed backend for eve's per-agent isolated execution environments.
The new commands are the easy part. The change worth reviewing is that the token your deploy job already holds can now edit DNS records, renew a domain and add a project member, all with clean JSON output.
Reality
A two-week, $1m escape challenge against Vercel's Firecracker sandbox produced 1,285 reports. The most valuable one hit the Linux kernel networking stack that many clouds use to isolate tenants, and its CVEs are pending.
Reality
The Run SDK swaps eval's ambient authority for a worker-thread sandbox with narrow host functions and resumable interrupts. The replay semantics are the part to read twice.
Reality
The Next.js team's closability agent reads each issue's conversation, searches the history and retries the reproduction on three releases, then hands a confidence score and its evidence to a maintainer who owns the close decision.
Reality
Devin Outposts on Modal moves code execution into infrastructure the customer runs, which makes a sandbox vendor, not a model vendor, the thing platform teams must procure and secure.
Reality
The open-source framework ships durable execution, sandboxing, approvals, subagents and evals in public preview. If the bet lands, your in-house harness is now maintenance.
Reality