X · by OrcDev

TanStack AI subagents, chosen by Jev

Which models or agents run, in parallel, sequence or mixed.

OrcDev

@orcdev

TanStack AI just shipped subagents. Jev picks which models / agents should run for the task, in parallel, in sequence, or mixed. Best Jev use case I've seen so far. TanStack team cooked. 🔥

Sep 24, 2026 · 92 likesOpen on X

OrcDev reports that TanStack AI shipped subagents, with Jev picking which models or agents should run for a task, in parallel, in sequence or mixed. He calls it the best Jev use case he has seen.

Open the source

More like this

Desert Ant Labs

@desertantlabs

Jev + on-device models = results in seconds with no LLM in the loop. Quick demo app to show the possibilities. Drop in an audio file: Ear detects the language, Voz transcribes it and Redact removes PII. Then @typesafeai's Jev makes about 20 decisions in one call in milliseconds, and picks which of our on-device models to run. Voice memo to to-do list. Meeting to redacted transcript. Podcast to clips.

XRouting and model choice

Pick

On-device audio, no LLM in the loop

Decisions: ~20 per call

Sarah Drasner

@sarah_edo

🎇 I made a small Chrome extension: a side panel that drives any site's WebMCP tools with Jev! When you type, on every keystroke it picks the relevant page's tool, fills in the arguments, and tells you how sure it is. Here it is grocery shopping:

XRouting and model choice

Pick

A side panel that drives any site's WebMCP tools

Milind S

@milindlabs

got @typesafeai's new model Jev as a chief of staff for bots Jev reads the task, wakes the right teammates off the bench and gives each one the right model It is possible on OpenMausBot as it supports all the LLMs from your existing subscriptions Jev as a decision engine is great

XRouting and model choice

TanStack AI subagents, chosen by Jev

More like this

On-device audio, no LLM in the loop

A side panel that drives any site's WebMCP tools

A chief of staff for bots