Fetching from the wire…
01
02
03
04
05
06
07
08
Infra2026-06-27 · source-backed
Vercel's Ship 2026 recap frames the next decade around infrastructure "designed for agents from the start," building on AI SDK 7 primitives like durability, approvals, and sandboxes. (Vercel) They also shipped vercel metrics to query Web Analytics from the CLI, making product data agent-accessible. (Vercel changelog) I deploy on Vercel, so I'll say the quiet part: the approvals and sandbox primitives map directly onto the "assume compromise, contain it" security model from the Top 5. The platform that gives you a clean human-gate and a real sandbox out of the box saves you from rolling your own.
Each link below shares sources, entities, or timing with this story.
Announced at Vercel Ship 2026, AI SDK 7 converts a model-abstraction library into a toolkit for agents that reason, call tools, run across many turns, and work across files and sandboxes, behind one provider-agnostic interface. Vercel paired it with Eve (define agent instructi...
Guillermo Rauch posted on August 3 that Vercel built an internal agent called @v that "powers day-to-day operations" and is an expert in finance, comms, docs, marketing, engineering and business analytics. Daily interactions and token use both growing exponentially. It's seede...
A September 14 changelog says the harness layer uses native subscription logins for Claude Code, Cline, Codex, Cursor, fx, GitHub Copilot, Grok Build, OpenCode and Pi, with no code changes needed (Vercel). Credentials stay on the host and real tokens get injected at the host b...
Open issues on the AI SDK went from 1,022 to 844 in four weeks. That's the number I'd lead with if I were writing this post, and Vercel did. Vercel published the internals of the system it built to maintain the AI SDK, a repo with over 20 million npm downloads a week, 26,000+...
npx deepsec init now sets up a repo and runs its first review in a single command: creates an isolated .deepsec/ workspace, configures model access via AI Gateway or custom keys, generates a codebase description and attack-surface map, runs pattern scans for coverage gaps, the...
Released August 6 by InclusionAI, it's a native hybrid-reasoning MoE with switchable Thinking and Instant modes, native function calling, prompt caching and 256K context, aimed at resource-constrained and fully local deployment (demoed against obsidian-cli over a local notes r...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.