X · by acenik10

TypeSafe launches Jev

A millisecond, low-cost decision model for agents.

Nikkhil Narang

@acenik10

Your agent doesn't need a bigger brain. It needs a faster one. Most agent decisions are tiny — urgent or not, which queue, yes/no. We run them through frontier models anyway. TypeSafe's new Jev does it in milliseconds for a fraction of the cost. #AIAgents #Jev

Sep 24, 2026 · 0 likesOpen on X

acenik10 covers TypeSafe’s launch of Jev as a millisecond-level, low-cost agent decision model.

Open the source

More like this

OpenRouter
@OpenRouter
1/ Jev, a decision model by @typesafeai, sparked a burst of projects and discussion. We tested it using Ori Eval against popular LLMs on OpenRouter at judging. Jev was >5x faster than the next fastest model, and even its slowest requests beat every other model's median.
XBenchmarks and evals
OpenRouter’s Ori Eval
Speed
>5× the next fastest
nader dabit
@dabit3
Also have been playing with @typesafeai Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms
XBenchmarks and evals
Keystroke oracle
ILIAS ISM
@illyism
Now using @typesafeai Jev in http://aiseotracker.com, http://linkdr.com, http://genppt.com, etc AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast! Also for regular LLM calls, it is around 10x faster, 50% cheaper
XBenchmarks and evals
Hard-coded rules moved to Jev

TypeSafe launches Jev

More like this

OpenRouter’s Ori Eval

Keystroke oracle

Hard-coded rules moved to Jev