Organization repository on GitHub
- Forks
- 4
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Workshop: decisões rápidas
A Laravel and Livewire workshop demo that runs a Twitch-style live chat through four moderation setups in parallel: a conventional LLM agent, the Decisions API decision model, a local Laya model and OpenAI Moderation, comparing accuracy, latency and cost.
- Stars
- 10
- Language
- HTML
- Reading time
- 2 min
- Published by
- Community
- Author
- beerandcodeteam
- Last verified
- Oct 2026
Highlights
- A Twitch-style live screen with working chat where every message passes through an AI moderator.
- Four approaches compared side by side on the same block-or-release decision.
- Decision models included: the Decisions API (probability-only model) and local Laya, plus a conventional LLM agent and OpenAI Moderation.
- Stack: Laravel 13, Livewire 4 (single-file page), Blaze, Tailwind CSS 4, Laravel AI SDK, SQLite and a database queue.
- Measures hit rate, time and cost for each decision approach; all content is in Portuguese.
Watch out
README and GitHub metadata reviewed 2026-10-17; the README is in Portuguese and the excerpt truncates the requirements table, so exact PHP extensions, env variables, results and model IDs are not evidenced. No license is listed in the digest metadata.
Questions about this entry
Short answers drawn from the linked project or page.
A live-screen (Twitch-style) app with a working chat where every message passes through an AI moderator, built to compare different ways of making the same block-or-release decision while measuring hit rate, time and cost.
One of the four compared approaches is the Decisions API, described as a model that only returns probabilities. The digest does not name Jev explicitly in that row, so the mapping from row to product should be confirmed in the repo.
Laravel 13 with Livewire 4 (single-file page), Blaze, Tailwind CSS 4, the Laravel AI SDK, SQLite and a database queue, per the README. The repo's language field is HTML.
Per the README: a conventional LLM (an agent with reasoning and tools), the Decisions API (probability-only model), a local decision model (Laya, on your machine), and the ready-made OpenAI Moderation endpoint.
The requirements table shows PHP 8.3 or higher with the pdo_sqlite and pcntl extensions; more requirements and env variables are listed in the README sections the digest excerpt truncates. API keys may be needed for the hosted approaches.
The README has a benchmark measurements section plus a dataset of messages, and the site measures accuracy, time and cost, but the digest excerpt truncates before those numbers, so no results are reported here.
The beerandcodeteam organisation publishes it; digest metadata shows 10 stars, 4 forks, creation 2026-10-12 and last push 2026-10-14, with no license field listed.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Building a contextual brand-safety scorer on Jev from scratch.
X: A website slop detector that checks 35 tells in 243 ms
X: Breaking, golden nugget, or slop
X: A filter for reply-guy comments
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-notPythonEleven 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-coursePythonFive self-contained Jev demos, one folder each: Jev fetching for Claude, Jev and Laya grading 500 AI answers, a prompt-injection review gate, and two fine-tuned decider comparisons against Jev.
Jev Demos & Experiments#community#python#demos
Community
mani-aiml/jev-demosPython
mani-aiml/jev-demosPythonA learning lab for decision models: TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls, while Claude handles the hard cases. It ships an interactive site, a benchmark, calibration tests and docs.
Jev Demos & Experiments#community#github#benchmark
A Bun workspace pairing a typed decision API over System One providers with a React arcade where decision models play games and every call is stored and ranked. The sample code calls Jev through OpenRouter with boolean, choice and score questions.
Jev Demos & Experiments#community#github#typescript
Community
desplega-ai/system-oneTypeScript
desplega-ai/system-oneTypeScriptA Python dispatcher skeleton for TypeSafe System One (Jev) that turns typed signatures into batched questions, plus a Playwright browser harness that measures the dispatcher against ground truth.
Jev Demos & Experiments#community#github#python
Community
monkey1sai/jev-systemone-labPython
monkey1sai/jev-systemone-labPythonFrom 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.