User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
SystemOne Demo: Winged Dash
A browser game for exploring fast, structured decisions with Laya: play the bird yourself, race a rule-based baseline, or watch a real decision model choose between flap and wait on seeded pipe sequences.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- NitroAMD
- Last verified
- Oct 2026
Used inJev for Gaming
Highlights
- Fixed 60 Hz simulation with seeded pipe sequences; models receive bird position and velocity, physics constants and visible pipes.
- No screenshots or generated chat are used as input: the decision model works from numeric state data only.
- Play as You, or watch the Rule bot, which the README calls explicitly a baseline rather than a neural model.
- Python 3.10+ is enough to play: no packages, model downloads, Node.js or build step are required; run python server.py.
- MIT licensed, created and pushed 2026-10-05; the README links an architecture document and a contributing guide.
Quickstart
bash
git clone https://github.com/NitroAMD/SystemOne-Demo.git
cd SystemOne-Demo
python server.pyWatch out
README reviewed 2026-10-17; the excerpt ends inside the interface-preview details, and the screenshot shows an explicitly labelled planning test adapter, so the full model path is not captured. No benchmarks appear in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A browser game for exploring fast, structured decisions with Laya. You can play the bird yourself, compare a rule-based baseline, or let a real decision model choose between flap and wait.
Through numeric state data: bird position and velocity, physics constants and the visible pipes, in a fixed 60 Hz simulation with seeded pipe sequences. The README says it does not use screenshots or generated chat responses.
Clone the repository, then run python server.py and open http://127.0.0.1:8765/ in a browser. Python 3.10+ is sufficient for human play and the rule bot; no packages, model downloads, Node.js or build step are needed.
The rule bot is explicitly a baseline, not a neural model, per the README. The decision model is the option that really chooses actions, and the game is built to compare the two alongside human play.
Playing, or watching the rule bot, needs no key or download at all. The README's quick start mentions only the Python server; what the real decision-model path requires is not captured in the digest excerpt.
NitroAMD published it under the MIT license, with the repository created and pushed on 2026-10-05 and zero stars at sweep time; an architecture document and a contributing guide are linked.
No. The README labels the interface preview as using an explicitly labelled planning test adapter, so it illustrates the interface rather than a verified production model run.
More Jev resources like this
An open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Community
rehan-remade/open-anniePython
rehan-remade/open-anniePythonA French 3D browser defense game used as a test bench for decisions under uncertainty: JEV (TypeSafe AI) estimates from a text description whether a silhouette is a zombie or a survivor, and deterministic code decides whether to shoot.
Jev Demos & Experiments#community#github#game
Community
Pablositoo/dernier-abriPython
Pablositoo/dernier-abriPythonA real-time alien shooter whose player is driven by Jev System 1: instead of hard-coded movement and shooting logic, the AI reads the game state and makes deterministic picks between left, right or stay, and between firing or holding fire.
Jev Demos & Experiments#community#github#python
A MuJoCo city simulation where one, two or four camera-observed drones pursue a target: each role asks Jev role-specific typed questions while deterministic mission navigation, safety guards and motor control run independently at 50 Hz.
Jev Demos & Experiments#community#github#python
Community
YongLD/Multi-UAV-JEVPython
YongLD/Multi-UAV-JEVPythonA Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonA browser playground for S1-CED, a small decision model you give a piece of text plus typed questions — yes/no, which-of, or a 0-3 score — and it answers with a probability per option and whether it is confident enough to act or a human should check. Runs on CPU; no GPU or account needed.
Jev Demos & Experiments#community#github#python
Community
ai-yatra/s1ced-playgroundPython
ai-yatra/s1ced-playgroundPythonFrom 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.