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
bleep Broadcast Delay Demo
A live broadcast-delay demo powered by Jev: you talk into a microphone and each sentence prints with its language tagged, offensive words masked one emoji per word, personal information redacted, and trash-talk sentences elided, judged by Jev in roughly 150 milliseconds.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- tmclnk
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open source
Highlights
- Replaces a broadcaster's seven-second manual delay button with a model that judges each spoken sentence before it would reach air.
- Offensive words are masked one emoji per word, redacted PII shows as block characters, and trash-talk sentences are elided entirely.
- Each sentence prints a status line with Jev's latency, token count, dollar cost, plus the Whisper transcription time.
- Sample output shows Jev at 107 to 212 milliseconds and 0.000045 to 0.000063 dollars per sentence, with Whisper taking 1.7 to 2.1 seconds.
Watch out
README reviewed 2026-10-17; the captured excerpt shows demo output and the pitch, not setup, dependencies, key configuration or license. Ground any run-it-yourself expectations on the fact that no install steps appear.
Questions about this entry
Short answers drawn from the linked project or page.
A live broadcast-delay demo powered by Jev, TypeSafe's System One model: it replaces a broadcaster's manual seven-second dump button with model judgments on each spoken sentence.
Each transcribed sentence is judged: its language is tagged, offensive words are masked, personal information is redacted, and sentences where you are talking badly about someone are elided entirely.
One monkey emoji replaces each word of an offensive word or phrase, block-out characters mark redacted PII, and a full line of block characters means the sentence was cut for trash talk.
The sample status lines show Jev judging in 107 to 212 milliseconds for 0.000045 to 0.000063 dollars per sentence, while Whisper transcription takes 1.7 to 2.1 seconds.
Yes. The digest's sample output includes English and German sentences, each tagged with its detected language on the status line.
The captured README shows demo output and the pitch but no setup, install or configuration steps, so running it is not documented in the digest.
tmclnk published it as a Python project with 0 stars and no license; it was created and last pushed on 2026-10-09, per the digest metadata.
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
An 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 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.
Jev Demos & Experiments#community#github#php
Community
beerandcodeteam/workshop-jevHTML
beerandcodeteam/workshop-jevHTMLA 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 MuJoCo city simulation where one, two or four camera-observed drones pursue a target: each role asks Jev role-specific typed questions while deterministic mission navigation, safety guards and motor control run independently at 50 Hz.
Jev Demos & Experiments#community#github#python
Community
YongLD/Multi-UAV-JEVPython
YongLD/Multi-UAV-JEVPythonA 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.