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
System One Model PoC
A small proof-of-concept app that runs local Laya and external System One-family APIs in one judgment UI: it executes typed questions against a state and compares choice probabilities, yes/no probabilities and ordinal scores across providers.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- keispace
- Last verified
- Oct 2026
Works forJev for Evaluation
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Runs local Laya on MPS or CPU and calls Jev two ways, Decisions API with typesafe/jev-1.13 and TypeSafe API with jev-latest, from one UI.
- Executes typed questions rather than chat: it compares option probabilities, true/false probabilities and ordinal scores across the selected models.
- Keys live in .env as DECISION_ORG_API_KEY and TYPESAFE_API_KEY; they are used only in the Authorization Bearer header, never in the browser or health output.
- If a provider key is missing, only that Jev entry is disabled; local Laya and the other provider keep working.
- Python 3.13 venv setup with requirements.txt; the app starts via .venv/bin/python app.py. 0 stars, created 2026-10-01, no license listed.
Quickstart
bash
python3.13 -m venv .venv
.venv/bin/python -m pip install --upgrade pip
.venv/bin/python -m pip install -r requirements.txtWatch out
README reviewed 2026-10-17; it is written in Korean and the captured excerpt cuts off at the default-address line, so the routes, question schema, comparison output and screenshots are not available, and no license is listed.
Questions about this entry
Short answers drawn from the linked project or page.
A small proof-of-concept app that selects and calls local Laya and external System One-family APIs from one judgment UI, executing typed questions against a state instead of holding a generative chat.
Three entries: local Laya Multilingual on this Mac's MPS or CPU, Jev 1.13 through the Decisions API, and Jev latest through the TypeSafe API; the two Jev entries use different providers and keys.
You put DECISION_ORG_API_KEY and TYPESAFE_API_KEY in a .env file at the project root. Keys are read once at startup and used only in the Authorization Bearer header, never in the browser, health response or results.
Each missing key disables only that provider's Jev entry, so local Laya and any provider with a configured key continue to work, according to the README.
The README uses a Python 3.13 virtual environment: create .venv, upgrade pip, install requirements.txt, then run .venv/bin/python app.py; the captured text cuts off before the default address is shown.
No. The README says local Laya uses model weights from the Hugging Face cache, and the Laya and Hugging Face runtime downloads what is missing automatically on first run.
The excerpt stops at the startup section, so the UI routes, question definitions, comparison output format, license and screenshots are not available in the digest. GitHub metadata shows 0 stars.
More Jev resources like this
A small Python app that asks whether a headline is Onion-style satire or real news. Jev runs through TypeSafe's API with your own key and is compared side by side with AnyJev L0 and raw Qwen3-8B running locally, with an option to swap the answer order.
Jev Demos & Experiments#community#github#python
Community
andrisgauracs/onion-or-notPython
andrisgauracs/onion-or-notPythonA local workbench for System One-style models on Apple Silicon Macs: it serves Laya through MLX or Core ML behind a Jev-compatible /v1/systemone endpoint, proxies other Jev-compatible servers like Jeff and Kev, recommends models and evaluates them on Japanese data.
Jev Tools & CLIs#community#github#python
Community
katya4oyu/systemone-workbenchPython
katya4oyu/systemone-workbenchPythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonAn 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 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-ragPythonEleven small runnable projects for learning Jev and other System One decision models, each lesson pairing a one-command web demo with a whiteboard and README, from the three question types through jobs sorting and contract review to Jev inside a SQL query. Every demo makes live API calls.
Jev Demos & Experiments#community#github#python
Community
aianytime/jev-crash-coursePython
aianytime/jev-crash-coursePythonFrom 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.