Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more
EmbodiedJev
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.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- FBddcz
- Added
- 2026-09-22
Highlights
- Three simulated tasks run on MuJoCo with a Franka Panda, and the built-in rule baseline needs no API key, GPU, or model weights.
- Jev receives structured text plus RGB-D detector coordinates rather than screenshots, and picks phases, skills, or short XYZ and gripper steps.
- Model comparison runs two or three configurations on the same task, seed, and action budget and aligns replays by simulation time.
- Candidate actions are rehearsed in a simulation copy that intercepts configured collisions and grasp loss before execution.
- Connections cover TypeSafe Jev, Claude, any OpenAI-compatible API, and a local MiniCPM5-2B, with keys kept in the system keychain.
Quickstart
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -e .
npm ci && npm run build
embodied-jev serve --port 8090Watch out
MIT for the original code, with Franka Panda assets under Apache-2.0. Needs Python 3.11+ and Node.js 22.12+, plus a TypeSafe key for Jev; model weights are not bundled and the project is independent of TypeSafe.
More like this
From the community
Posts from builders shipping with Jev right now.
Jev lands on OpenRouter
700 leads scored for $0.09
JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more
Beating Gemini Flash Lite on an eval
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)
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
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



