X · by QingQ77
A project where Jev chooses how much reasoning runs before generation.
Geek Lite
@QingQ77
Codex 一旦开跑，推理档位就钉死不动，读个文件也用最高强度烧 token,这个项目让 Jev 在每次生成前重新挑档位。 github.com/miuuyy/Astra-A…
Sep 24, 2026 · 7 likesOpen on X
QingQ77 shares a project that lets Jev dynamically choose the reasoning level before generation.
Open the source
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.
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
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