Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
JEVfire
An independent CUDA and vLLM take on parallel typed decisions: it scores verified single-token labels with the model's own head and assembles JSON in code.
- Category
- Practices & Patterns
- Published by
- Community
- Author
- kikoncuo
- Added
- 2026-09-22
Tagscommunitypythonjavascriptopen-modelsbenchmarksgames
Highlights
- Scores verified single-token labels with the pretrained model's own head and maps winners to allowed values, with no second model.
- A 28-field fresh-prefix task ran in 496.9 ms versus 5,113.1 ms for constrained JSON on the same 27B model, 10.29x faster.
- The browser Mario demo cleared World 1-1 in 40.12 s at 71.26 ms mean worker inference on an M4 Max with WebLLM.
- Supplied schemas define keys and choices, so the model cannot invent fields or out-of-set values, though it can pick a wrong allowed value.
- Fixtures, per-request timings, and methodology are published, including a 2,622-request tuning campaign.
Quickstart
bash
python -m pip install -e '.[dev]'
python examples/racing_agent.py --steps 8Watch out
MIT-licensed. Independent project, not affiliated with TypeSafe; the CUDA numbers cover synthetic boolean and enum fixtures rather than arbitrary JSON, and the browser demo needs a roughly 450 MB model download.
More like this
3.6kGitHub stars
An independent baseline that reads typed option probabilities straight from a frozen Qwen3.5-4B's logits in one forward pass, reproducing Jev's interface pattern with open models rather than Jev's undisclosed model or training.
Practices & Patterns#community#python#open-models
CommunitySemIf
3.2kGitHub stars
Apache-licensed, locally runnable Jev-style decision models (0.8B, 4B, 9B on Qwen3.5) with released weights, training code, a System One-compatible server, frozen eval suites, and a playground.
Practices & Patterns#community#python#open-models
Communitykev
296GitHub stars
An independent open reproduction of the System One model class: Qwen3.5-based 2B and 35B mixture-of-experts models that return typed Choice, Score, and Noul probabilities in one forward pass, with nothing distilled from Jev.
Practices & Patterns#community#python#open-models
Communitydecider
From the community
Posts from builders shipping with Jev right now.
Browser Use Ultrafast, powered by Jev
A really smart switch statement
hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by 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
When a designer gets Jev
when a designer gets access to Jev
Full Jev video tutorial
Full Jev Tutorial What it is, how you can build with it and what new applications it can unlock → 0:00 Intro → 0:34 Jev explained → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
The case against Jev-scored compaction
This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the 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
Classifying rows in DuckDB
I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!
