Ran @typesafeai's Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite. It won both on quality (saturated the eval) and speed (6x)
RoboJEV
Two-stage Jev control of a Franka Panda in MuJoCo: Jev selects a task intent, then X/Y/Z directions and a gripper command executed against real contacts, with 43 of 50 Jev episodes succeeding versus 48 of 50 for a rule baseline.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- lykycy123
- Added
- 2026-09-22
Tagscommunitypythonroboticsevaluationbenchmarks
Highlights
- JEV receives structured simulator state, not images, and every task has independent physical success checks, so model answers cannot declare success.
- Across five tasks with fixed seeds 0-9, JEV succeeded in 43 of 50 episodes versus 48 of 50 for the rule baseline.
- The gaps: stack on a pedestal 8/10 versus 10/10 and gate pick & place 5/10 versus the baseline's 8/10.
- The showcase plays success and failure recordings, which follow simulation time with API waits omitted; stack uses a fixed pedestal.
- Real JEV calls use jev-1.13.0 at https://api.typesafe.ai/v1/systemone; CPU physics and the rule policy need no GPU or API key.
Quickstart
bash
conda env create -f environment.yml
python -m pip install -e '.[test,video]'
cp .env.example .env # then set TYPESAFE_API_KEYWatch out
Apache-2.0 (MuJoCo Menagerie robot assets keep their own license); real JEV needs a TypeSafe API key and incurs charges, Linux with Python 3.11 is the tested platform, and the console needs Linux or WSL2.
More like this
181GitHub stars
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Cookbooks & Demos#community#python#robotics
Communityembodied-jev
83GitHub stars
A camera-only MuJoCo quadrotor that uses Jev for tactical maneuvers at 2.5 Hz while classical perception and a 50 Hz reflex layer keep safety outside Jev, clearing a five-station course.
Cookbooks & Demos#community#python#robotics
Communityjev-drone
54GitHub stars
A fine-grained robot control study loop for LIBERO tasks: Jev layers an intent, a contact or motion family, and one of 27 control inputs, while reversible MuJoCo previews evaluate each candidate before execution.
Cookbooks & Demos#community#python#robotics
Communityjev-libero
From the community
Posts from builders shipping with Jev right now.
Beating Gemini Flash Lite on an eval
Browser Use Ultrafast, powered by Jev
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 ↓
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