Organization repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Models & Reimplementations
Robo Jev
A fast, single-pass 2B System 1 model for robots' physical judgment: it reads a short text of what a robot senses and returns probabilities for the questions that matter in the moment, scoring 0.81 on its own benchmark against TypeSafe Jev's 0.28.
- Stars
- 7
- Language
- Python
- License
- APACHE-2.0
- Reading time
- 2 min
- Published by
- Community
- Author
- STEERIX-home
- Last verified
- Oct 2026
Used inJev for Robotics & Hardware
- Languages
- Python
- Capabilities
- Open source
Highlights
- Reads a short text of what a robot senses and answers moment questions with a probability for every answer.
- Example questions: will the glass tip if I brake now? does the person reach my path first? did the part seat?
- On the repo's physical-judgment benchmark: robo-jev v0.7 (2B) 0.81 versus TypeSafe Jev 0.28 and Liquid d1 0.17.
- General reading (BoolQ + MultiNLI): robo-jev 0.71 while TypeSafe Jev 0.91 and Liquid d1 0.93 lead there.
- Apache-2.0 Python: 7 stars, created 2026-09-17, last pushed 2026-10-17, the day this entry was written.
Watch out
README reviewed 2026-10-17; the physical-judgment benchmark is the project's own held-out set, and the digest truncates right after the metric definition, so training data, weights, and serving instructions are not visible. Rival scores are quoted from the README's figures.
Questions about this entry
Short answers drawn from the linked project or page.
A fast, single-pass 2B System 1 model from STEERIX-home for robots' physical judgment: it reads a short text description of what a robot senses and answers the questions that matter in the moment with a probability for every answer.
Physical-judgment questions phrased as text, such as whether the glass will tip if the robot brakes now, whether a person reaches its path first, or whether a part seated correctly.
On robo-jev's own held-out physical-judgment benchmark, robo-jev v0.7 scores 0.81 versus 0.28 for TypeSafe Jev. On general reading (BoolQ + MultiNLI) Jev leads at 0.91 to robo-jev's 0.71 — a specialization trade-off.
It is skill against always answering 50%: 0 is a coin flip and 1 is perfect, measured on robo-jev's held-out situations. An untrained Qwen3.5-2B scores -0.15 on the same scale.
No — it is an independent open model that benchmarks itself against TypeSafe Jev and other decision models including Liquid d1, Microsoft-Decision-1, Together Tev1 4B, and Upstage Solar Decide. It reuses the System One idea rather than Jev's API.
The README's table shows general reading well behind the wider models (0.71 versus 0.91-0.93), so it is built for short physical judgments rather than general language understanding. All benchmark figures are the project's own.
It is an Apache-2.0 Python repository from STEERIX-home with 7 stars, created 2026-09-17 and last pushed 2026-10-17. The digest truncates before setup, so weights and serving instructions are not documented here.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Pick Verify: a single decision at the warehouse pick station catches confusable picks.
Show HN: Verifying robot picks with a decision modelRead the thread on Hacker NewsX: A dual-arm robot with Jev in the middle layer
YouTube: Dan Makes Things drives an ESP32 robot with Jev decisions.
More Jev resources like this
A small, fast decision model — a system one model — for agentic workflows from Strands Labs: it picks between options or rates on a scale faster than an LLM and returns a calibrated confidence with every decision.
Jev Models & Reimplementations#community#github#python
Community
strands-labs/strands-deciderPython
strands-labs/strands-deciderPythonAn independent open-source pipeline that gives Jev vision: it detects and tracks objects in images, video, and RGB-D camera feeds, then asks Jev a typed question about each relevant object and prints the chosen answer with its confidence.
Jev Tools & CLIs#community#github#python
Community
CharlesFeng0314/JEV_seesPython
CharlesFeng0314/JEV_seesPythonSystem One models from first principles by Qi Li and Xinchao Wang at the National University of Singapore: give Jeva a state and typed questions and it returns candidate probabilities, a Boolean probability, or an expected rubric score, with reusable option memory.
Jev Models & Reimplementations#community#github#python
Community
liqiiiii/jevaPython
liqiiiii/jevaPythonAn open-source, local alternative to Jev: System-One decision models that answer the POST /v1/systemone shape — choice, yes/no, or score — for general decisions and browser-agent steps. Models ship as OpenJev-1.7B, 4B, and 8B, with a pip-installable Python package.
Jev Models & Reimplementations#community#github#python
Community
alanhuangyoo/openjevPython
alanhuangyoo/openjevPythonA generation-free typed-decision engine on Sarvam's Indic models: options become lettered slots, the answer is read from those letters' logits, and one state prefill is amortised across many cheap questions. Its README says the interface pattern is TypeSafe's Jev.
Jev Models & Reimplementations#community#github#python
Community
sagar-tamang/sarvam-jevPython
sagar-tamang/sarvam-jevPythonAn open System One decision model from Interfaze-ai: give lev a state — text, a ticket, an email, or JSON — plus yes/no, choice, or score questions and it answers all of them in one forward pass from logits, returning calibrated probabilities and zero output tokens.
Jev Models & Reimplementations#community#github#python
Community
abhinavexists/levPython
abhinavexists/levPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.