User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
SystemOneStudio
A no-code training platform for judgment models: define a judgment task, import decision samples, build a training set, train candidate probabilities, verify calibration and publish a service. The README says phase P3 is in implementation with no real GPU evidence yet.
- Stars
- 1
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- cers-ai
- Last verified
- Oct 2026
- Languages
- Python
Highlights
- Zero-code flow: define a judgment task, import samples, build a training set, train candidate probabilities, verify calibration, publish a service.
- Three-class black/white/gray judgments with reason and evidence kept as optional audit fields.
- README status: P3 approved and in implementation; CPU data prep done, real GPU training and the release loop still unproven.
- Last full check per README: 106 frontend tests and a passing build; 907 Python tests passed, 1 GPU test skipped.
- Node 22 with npm and a fixed Python 3.11 workspace managed by uv; API on 9969, Vite on 5174.
Quickstart
bash
npm ci
uv sync --all-packagesWatch out
README and GitHub metadata reviewed 2026-10-17; the README is written in Chinese and the digest truncates its run instructions mid-block. The project states most of the seven-step product, real GPU training and the release loop were still unfinished at capture time.
Questions about this entry
Short answers drawn from the linked project or page.
A no-code training platform for judgment models: define a custom judgment task, import decision samples, build a training set, train candidate probabilities, verify calibration and publish a service, with a web control plane.
The README says phase P3 is approved and being implemented. The engineering baseline and V3 CPU data preparation are complete, but real GPU spikes, the full seven-step product and the release loop were still unfinished at capture time.
106 frontend tests and a passing build, plus 907 passed Python tests with 1 GPU test skipped and 1 pre-existing warning. The development machine had no NVIDIA GPU, so GPU paths were not exercised.
Three-class black, white and gray judgments, with reason and evidence kept only as optional audit fields. Training uses candidate probabilities with cross-entropy and Brier terms, temperature calibration, and AUTO or REVIEW policy routing.
The README excludes an assistant, business templates, a custom head, RLCD-like training and delegated sub-agents. The plan is a real GPU CLI first and the full UI later, with Transformers merged models accepted before GGUF.
With Node 22 and uv: npm ci, uv sync --all-packages, then npm run dev:api and npm run dev in separate terminals. The API defaults to port 9969 and Vite to 5174; npm run up is a CPU single-studio Compose entry with a known image-build break.
No. The README states the demo and the old generated training code cannot serve as V3 acceptance evidence, and that real training, merged loading, quantization, prediction and performance still lacked V3 evidence when captured.
More Jev resources like this
A local decision engine for AI agents and software developers, built on the System One architecture in TypeSafe's Jev style and running fully offline through Ollama 0.35+. Ships a CLI, an MCP server and a Python library for error triage, diff review, shell guardrails and routing.
Jev Tools & CLIs#community#github#python
Community
beliciobcardoso/systemone_gatePython
beliciobcardoso/systemone_gatePythonConfidence-gated email triage for founders, powered by Jev: it sorts each message into urgent, wait or noise and only auto-acts when sure. Doubtful mail goes to a morning digest with suggested actions for one-tap approval.
Jev Tools & CLIs#community#github#python
Community
AdityaPagare619/inboxpilotPython
AdityaPagare619/inboxpilotPythonAn explainable intent router that cascades regex, TF-IDF with CatBoost, System One decision models (Laya, Jev, CLM) and a generative LLM fallback, answering from the cheapest engine able to decide and leaving a replayable decision record. Runs fully local.
Jev Tools & CLIs#community#github#python
An independent open-source pipeline that gives Jev vision: it detects and tracks objects in images, video, and RGB-D camera feeds, then asks Jev a typed question about each relevant object and prints the chosen answer with its confidence.
Jev Tools & CLIs#community#github#python
Community
CharlesFeng0314/JEV_seesPython
CharlesFeng0314/JEV_seesPythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA 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-onePythonFrom 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.