User repository on GitHub
An open-source, efficient System I decision model for autonomous driving.
- Forks
- 3
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Models & Reimplementations
DriveJev
An open-source System I decision model for autonomous driving: DriveJev scores every offered driving behaviour with a probability instead of generating text, and the demo clips show it holding, yielding, and proceeding in the JevPilot simulator.
- Stars
- 94
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- benmagnifico
- Last verified
- Oct 2026
- Languages
- JavaScript
- Capabilities
- Open source
Highlights
- README subtitle: an efficient System I decision model for autonomous driving, with DriveJev 1.0 driving in the JevPilot simulator.
- Decisions show the front camera with a tele inset and the probability of every offered behaviour.
- Six demo clips: an oncoming left turn, a 4-way stop with three cars, a red-light runner, a hidden pedestrian, exit-crosswalk pedestrians, and cut-ins.
- The project states every demo drive reached its destination with no collision and no violation.
- GitHub: 90 stars, 3 forks, JavaScript, MIT, created 2026-10-01, last pushed 2026-10-03; weights at huggingface.co/benmagnifico/DriveJev-4B.
Watch out
README reviewed 2026-10-17 and truncated mid-caption in the decisions figure, so install steps, evaluation results, JevPilot setup, and pricing are not in the digest. The no-collision and no-violation statement is the project's own summary of six demo clips, not an independent evaluation.
Questions about this entry
Short answers drawn from the linked project or page.
An open-source System I decision model for autonomous driving from benmagnifico: instead of generating text it assigns a probability to every offered driving behaviour and the vehicle acts on the result.
Its README calls it a System I decision model and the GitHub topics include jev, which puts it in the same decision-model class as TypeSafe's Jev. The digest shows no Jev API, endpoint, or TypeSafe dependency, so treat the link as a class resemblance.
The README links a Live demo anchor, an evaluation document at docs/evaluation.md, and the DriveJev-4B weights on Hugging Face. The digest excerpt includes no install commands or hardware requirements.
Six situations: an oncoming car turning left, a 4-way stop shared with three cars, a red-light runner after its green, a pedestrian stepping out from behind a parked car, two pedestrians on a turn's exit crosswalk, and three interstate cut-ins.
The project states that every drive reached its destination with no collision and no violation. That describes six selected demo clips in JevPilot and is not an independent benchmark or a road test.
MIT, per the GitHub metadata in the digest. The weights live in a separate Hugging Face repository (DriveJev-4B), so check that page for the terms that apply to the model files.
The digest truncates the decisions figure caption mid-sentence, so the install steps, evaluation numbers, JevPilot configuration, and any pricing are unavailable; metadata shows 90 stars, 3 forks, and a last push on 2026-10-03.
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 omni-modal Jev: a System One decision model that fine-tunes Qwen3.5 vision-language backbones with LoRA and decision heads, returning calibrated probabilities for typed questions about images, video, screens, audio, and robot scenes in one forward pass.
Jev Models & Reimplementations#community#github#multimodal
Community
tinnel123666888/OmniJevPython
tinnel123666888/OmniJevPythonSmall Jev-style decision models that read a state and typed questions and return a probability for every option in one forward pass without generating text; the 0.75B and 4.2B versions speak TypeSafe's Jev API format at a median of about 50 ms per request on one H100.
Jev Models & Reimplementations#community#github#decision-model
Community
jiwidi/jiwoPython
jiwidi/jiwoPythonSystem 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/openjevPythonAn 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.