Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-08-15 · source-backed
Shipped August 13 to Pro, Business and Enterprise: ChatGPT and Codex can draw on activity memories from apps and websites on macOS, with per-app opt-in and review or delete controls. OpenAI This is Cursor's Google Workspace connector move, but reaching down to OS-level activity instead of named SaaS. If you run Codex on a machine holding client or employer data, audit which apps contribute before enabling it.
Each link below shares sources, entities, or timing with this story.
Six clients. One manifest. Zero vendor lock. Vercel published Agent Plugins 1.0.0 on August 6, an openly licensed spec that bundles Agent Skills and MCP servers behind a single portable manifest. The shape is deliberately boring: a plugin.json requiring only schemaVersion and...
Three things happened this month that only make sense together. Agent Plugins 1.0 shipped co-signed by six competitors: AWS, Anysphere, Microsoft, OpenAI, Vercel and Google (GitHub Changelog). It makes skills-plus-MCP bundles portable across clients. OpenAI's August 11 Codex c...
TechCrunch reports the July 23 macOS and Windows rollout, built on ChatGPT-Live. It drives ChatGPT Work and Codex, so you can direct several agents simultaneously by voice, and macOS "Appshots" let it read the frontmost window including alt-text. Global rollout to Plus, Pro, B...
ChatGPT Work fuses ChatGPT with Codex to generate documents, decks, and websites, plus native computer use that clicks, types, opens local apps, moves files, and runs multi-step workflows autonomously. Powered by GPT-5.6, rolling out to Pro/Enterprise/Edu first. It's the direc...
Shipped August 20 across iMessage, SMS and RCS, available on every tier including free, working inside ChatGPT Work and Codex modes, Apple silicon only. Sending requires per-message approval, but enabling it requires Full Disk Access plus contacts and automation permissions. r...
OpenAI released GPT-5.4 simultaneously across ChatGPT, API, and Codex — the first unified triple release. Built-in computer-use capabilities (build-run-verify-fix loop), 1.05M token context, and 33% fewer false claims vs GPT-5.2. A new experimental "Playwright Interactive" ski...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.