VQV Signal

OPEN SOURCE WATCH TECHNICAL

Turnstone adds iOS and Mac agent dispatch to its model-agnostic app

According to a post on X by @turnstone_ai, Turnstone now supports dispatching agents from iOS and Mac, and more than 100 people have used its mobile app. The app runs agents on open models such as Kimi, Qwen, GLM and DeepSeek, billed from one balance, or on existing ChatGPT and Claude subscriptions. The post presents the update as a way to start agents from a phone without being tied to a single model provider.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-16T05:35:00+00:00 Detected 2026-11-16T18:24:30+00:00
View original source

According to a post on X by @turnstone_ai, Turnstone now supports dispatching agents from iOS and Mac, and more than 100 people have used its mobile app. The app runs agents on open models such as Kimi, Qwen, GLM and DeepSeek, billed from one balance, or on existing ChatGPT and Claude subscriptions. The post presents the update as a way to start agents from a phone without being tied to a single model provider.

AI-assisted summary based on the listed source.

Turnstone says it now supports dispatching agents from iOS and Mac, and that more than 100 people have used its mobile app. It runs agents on open models such as Kimi, Qwen, GLM and DeepSeek from one balance, or on existing ChatGPT and Claude subscriptions. Why it matters: Users can drive agents from their phone...

The update is most relevant to people who run AI agents and want to launch them from a phone while choosing among several models. According to the post, users can work with open models or their existing ChatGPT and Claude subscriptions in the same app. Watch whether the mobile user count grows beyond the 100-plus figure the post gives, and whether the claims hold up in independent use.

Signal Strength 83% Technical label WATCH Public Interest 47 Category OPEN SOURCE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 60 Practical Impact Score 44 Novelty Interest Score 70 Consequence Score 10 Curiosity Score 16 Shareability Score 62

VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).