User repository on GitHub
System One Model API for Laya compatible with TypeSafe Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Repos & SDKs
Zulvis System One
A self-hosted System One API billed as drop-in compatible with TypeSafe Jev: a bidirectional encoder with direct decision heads returns calibrated probabilities and structured choices in a single forward pass of about 33 ms.
- Stars
- 1
- Language
- HTML
- Reading time
- 2 min
- Published by
- Community
- Author
- ZulfiFazhar
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- Drop-in TypeSafe Jev API for deterministic parallel decisions with calibrated probabilities, per the README.
- Uses a bidirectional encoder with direct decision heads for structured choices in one ~33 ms forward pass.
- Claims 0% hallucination and zero generative text, positioned as the opposite research direction to token-by-token models.
- Python 3.12 and FastAPI 0.115+ per the README badges, Docker-ready; the description frames it as an API for Laya.
- GitHub metadata: HTML repo, 1 star, created 2026-09-21 and pushed 2026-10-13; the README badge says Apache-2.0.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt cuts off mid-claim after the ~33 ms figure, and GitHub lists no license even though the README shows an Apache-2.0 badge. The performance claims are self-reported.
Questions about this entry
Short answers drawn from the linked project or page.
A System One model API by ZulfiFazhar described as drop-in compatible with TypeSafe Jev, producing deterministic parallel decisions with calibrated probabilities instead of generated text.
The GitHub description presents it as a System One model API for Laya compatible with TypeSafe Jev, so clients written against the Jev typed-decision shape could target it; the digest does not show the exact request format.
It uses a bidirectional encoder with direct decision heads to produce calibrated probabilities and structured choices in a single forward pass of roughly 33 ms.
0% hallucination and zero generative text, framing generative models as accumulating latency, cost and hallucination — figures that are self-reported and not independently verified here.
Python 3.12 and FastAPI 0.115+ per the README badges, Docker-ready per its badge, with the repository metadata showing HTML as the detected language.
The README badge says Apache-2.0, but the GitHub metadata declares no license; the digest captures only the badge, so verify the LICENSE file before relying on it.
From the repository description — 'System One Model API for Laya compatible with TypeSafe Jev' — and the README heading Zulvis System One; the digest adds no benchmarks or comparison data.
More Jev resources like this
A FastAPI backend from SiliconLabAI that serves an OpenAI-compatible chat and tool-calling API plus a Jev-style POST /v1/systemone endpoint for typed decisions, powered by cactus-needle on CPU edge devices. The first request downloads the Needle weights once.
Jev Repos & SDKs#community#github#python
Community
siliconlabai/openjev-cactusPython
siliconlabai/openjev-cactusPythonAn open-source, non-autoregressive System One decision engine inspired by TypeSafe AI: it evaluates state context against typed questions in a single forward pass, returning probability distributions and calibrated confidence without generating text.
Jev Repos & SDKs#community#github#python
Community
Atulmishra22/jev-litePython
Atulmishra22/jev-litePythonA System One layout optimizer for decision-model workloads: it reorders rows and fields so a prefix-caching backend reuses input computation, then returns per-record decisions in original order. Its bundled backend serves AutoTrust JEV-9B through vLLM.
Jev Repos & SDKs#community#github#python
Community
0814wdwd/solo_jevPython
0814wdwd/solo_jevPythonHTTP server for the Mica v0.5 4B Preview decision model: GGUF weights run through llama.cpp and answer noul, choice and score questions with calibrated probabilities over the TypeSafe /v1/systemone format.
Jev Repos & SDKs#community#github#python
Community
akivet/MicaPython
akivet/MicaPythonServing code for the Jeff 1.0 family of Jev-style decision models: a state, a typed question and its options go in, and one forward pass returns a probability for each option. Four open models from 4B to 31B parameters are served the same way.
Jev Repos & SDKs#community#github#python
Community
j-geuter/jeff-servePython
j-geuter/jeff-servePythonA frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.
Jev Repos & SDKs#community#github#python
Community
krishna-gogineni-765/deck31bPython
krishna-gogineni-765/deck31bPythonFrom 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.