Today we're launching @mastra `Harness`
`Harness` gives you a `Session` with plan/build modes.
It lets you manage thread lifecycle, spawn or fork subagents, approve tools per-call or session, ask user questions, queue/steer.
With skills, sandbox, browser, heartbeat. channels:
Shopify should work wherever merchants work.
We now have Claude, ChatGPT, and Perplexity connectors. If you prefer a CLI or IDE, our AI Toolkit works with Claude Code, Codex, and Cursor.
If you donโt have a store yet, vibe code one in v0, Manus, Replit, or Lovable.
As the recently expanded partnership with @AnthropicAI demonstrates, @SpaceX is offering AI compute as a service at significant scale.
We are in discussions with other companies to do the same.
Over time, especially with orbital data centers, we expect to serve AI at extremely high scale.
Claude (not Claude Code), what a joke of an app it is. Incapable of anything more than simple QA conversations due to โResponse incompleteโ errors.
Iโd like to admit Claude Code hooked me up. I was never a CLI person, but considering the amount of credits I get on a Pro plan, I am steering into CLI more and more as my @cursor_ai subscription burns in 3 days of moderate use.
Gemini 3.5 Flash is built to help you execute complex, agentic workflows.
3.5 Flash rivals flagship models to deliver frontier performance for agents and coding, at the lightning speeds you expect from the Flash series.
@AnthropicAI officially claims that the large codebase navigation method that saves tokens (RAG) is inferior to the eager and token-hungry GREP. Who would have thought? ๐
https://t.co/VCOOT9MSUe
"We expect this to be a major leap in model capability" โ @cursor_ai is training a completely new custom model from scratch on the @SpaceX Colossus 2's infrastructure ๐ฐ๏ธ
Thatโs such an interesting partnership. Eager to see how it turns out.