I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Laya
Open multilingual System 1 decision models with published checkpoints for choice, score and noul questions, plus a router that dispatches each request to the right checkpoint in one forward pass.
- Category
- Repos & SDKs
- Published by
- Community
- Author
- NandhaKishorM
- Added
- 2026-09-22
Tagscommunitypythonopen-modelsroutingclassification
Highlights
- Three checkpoints cover English (ModernBERT-large, 421M) and 100+ languages (mmBERT-base, 322M), with a Router picking per request.
- Answers typed choice, score and noul questions in one forward pass: 33 ms for one question and 7.2 ms per question batched on a T4.
- Trained with RLCD, reinforcement learning against strictly proper scoring rules, with a predict_shortlist path for many labels.
- The README reports Jev gave zero probability to the true label on 16% of DAIR Emotion examples and scored 0.425 on 77-label Banking77.
- Base checkpoints score near chance zero-shot (0.36 and 0.35 against a 0.318 baseline) while the fine-tuned checkpoint reaches 0.766.
Quickstart
python
import laya
from laya import Router
router = Router(preload=True)
state = {"body": "We were billed twice. Please refund the duplicate today."}
questions = {"department": {"type": "choice", "instructions": "Which department should handle this?", "criteria": {"billing": "invoices, payments, refunds", "technical": "bugs, outages", "sales": "pricing"}}}
res = router.predict(state, questions)
print(res["answers"]["department"]["choice"])Watch out
Apache-2.0, developed by Convai Innovations. Needs Python 3.10+ and a GPU for fast inference; Jev comparisons use different prompts and sample sizes, raw calibration is weak, and it is not affiliated with TypeSafe.
More like this
475GitHub stars
A local server and Python package that runs open models with Hugging Face Transformers or PyTorch and returns Choice, Score, and Noul answers read from next-token logits instead of generated JSON.
Repos & SDKs#community#python#open-models
Communitysimple-jev
425GitHub stars
An open, non-autoregressive System One model with published weights and a TypeSafe-compatible /v1/systemone API; the 395M-parameter OptionMarker checkpoint scores discrete and ordinal questions locally.
Repos & SDKs#community#python#open-models
Communityvon
From the community
Posts from builders shipping with Jev right now.
Trading bot, one decision per block
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
LLM-as-a-judge, sped up
Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Instant compaction with Jev
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
A Claude session from 1M to 86K tokens
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant