User repository on GitHub
jev 研究文档
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Guides & Articles
Jev × Laya Research Notes
A Chinese-language research collection on System One decision models: it compares JEV and Laya academically and operationally, maps enterprise adoption, teaches Laya locally from setup to fine-tuning, and reads the Laya source. Research finished 2026-09-24.
- Stars
- 0
- Reading time
- 2 min
- Published by
- Community
- Author
- amosli
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open source
Highlights
- Six main documents: JEV vs Laya comparison, enterprise deployment guide, Laya tutorial, reference list and Laya source reading.
- Every performance figure is labelled as locally reproduced, vendor-published or third-party; the local runs used an RTX 5060 Ti 8GB with laya 0.3.20.
- Covers cold-start tuning in five stages and production routing via decision tables, replay calibration and shadow mode.
- Includes internet finance and e-commerce adoption plans plus a 90-day enterprise rollout roadmap.
- Research completed 2026-09-24; Chinese-language Markdown, 0 stars, no license or language listed.
Watch out
README reviewed 2026-10-17 (research completion date 2026-09-24); the captured excerpt ends in the source-reading document index, and the notes' own figures mix self-run, vendor and third-party measurements, so the confidence labels matter when reusing any number.
Questions about this entry
Short answers drawn from the linked project or page.
A Chinese-language research catalogue on System One decision models: it compares JEV and Laya, explains how enterprises adopt them, teaches Laya locally and walks through Laya's source code.
Four audience layers: everyone starts with the JEV vs Laya comparison, architects get the enterprise guide, developers get the Laya tutorial, and people who want the internals read the source-code notes.
Every figure is labelled: locally reproduced means the author's own machine, an RTX 5060 Ti 8GB running laya 0.3.20; vendor-published means from the maker; third-party means independent tests.
Task-fit judgment, a model-selection decision tree, six LLM cooperation patterns, cost estimates, deployment forms, quality assurance, risk and compliance, plus internet finance and e-commerce plans and a 90-day roadmap.
Yes, one document covers a five-stage cold-start method from decision-surface engineering through probes, baselines, fine-tuning and flywheels, with production routing via decision tables, replay calibration and shadow mode.
No. It is amosli's personal research repository with no licence or language listed; it is third-party documentation about JEV and Laya, and its reference list marks which sources were verified by hand.
Research and writing were completed 2026-09-24; the README shows an RTX 5060 Ti and laya 0.3.20 as the reproduction environment, and the digest captured 0 stars and no forks.
More Jev resources like this
A link collection rather than a codebase: babybear-labs gathers Jev architecture reading, Laya alternatives and ports, playgrounds, tiny decision-model projects and apps built on System One decision models, with no README prose beyond the links.
Jev Guides & Articles#community#github#links
Community
babybear-labs/system-one
babybear-labs/system-oneA Korean Slidev course — 59 slides, 110 minutes plus deep-dive Q&A — with three standalone Jupyter notebooks that take Jev decision models from NLL/Brier/ECE calibration to training a Qwen-based Jev-compatible model with Unsloth and testing its HTTP API.
Jev Guides & Articles#community#github#korean
Community
heury/jevJupyter Notebook
heury/jevJupyter NotebookThe community hub for System One decision models, live at systemone.dev. It teaches building with models that answer typed questions about a program's state using calibrated probabilities instead of generated text, and its samples work unchanged with Clef and Jev.
Jev Guides & Articles#community#github#docs
Community
systemonedev/systemone.devPython
systemonedev/systemone.devPythonA timestamped benchmark and trading arena that replays resolved prediction markets: models commit to probabilities using only information available at the time, and realized P&L is the headline metric with Brier, log-loss and ECE as checks.
Jev Benchmarks & Evaluations#community#github#python
Community
ruyianry/JevGymPython
ruyianry/JevGymPythonThe code and data behind ProbabilityBench: text-based simulated worlds with exact class probabilities, so a decision model's reported probabilities can be compared directly with ground truth. An arXiv paper and a Hugging Face dataset accompany it.
Jev Benchmarks & Evaluations#community#github#benchmark
Community
ishida-lab/probabilitybenchPython
ishida-lab/probabilitybenchPythonA community-maintained directory of 221 Jev integrations, compatible decision models, System One SDKs, agent tools, and research; every listed project must be active — pushed within two weeks, 50+ stars, not archived — and it is labeled unofficial.
Jev Guides & Articles#community#github#directory
Community
VoltAgent/typesafe-jev-ecosystem
VoltAgent/typesafe-jev-ecosystemFrom 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.