Jev mood demo
Web demo where you talk nicely or nastily over time and a structured state, updated by Jev, tracks the character's mood.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
Jev mood demo is a small web app. According to the list summaries, you talk to it nicely or nastily over several turns, and a structured state tracks its mood as the conversation goes on. Jev presumably judges each message and the mood state is updated in code.
No README was available, so the exact questions and mood scale are not documented. It illustrates using a decision model to maintain structured state across a conversation rather than generating replies.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Is this message nice, neutral or nasty?(inferred) | — |
How it works
- The user sends a message
- Jev judges the message tone
- Code updates the mood state
- The UI shows the current mood
Strengths
- Shows structured state tracking without text generation
Caveats
- No README; details unknown
- Source availability unknown
At a glance
- Type
- App
- Status
- prototype
- Runtime
- Web app
Use cases and integrations
How curated lists describe it
Talk nicely or nastily over time; structured state tracks mood.
AnotiaWang/awesome-decision-modelsTalk nicely or nastily over time; structured state tracks the mood.
hellogumbo/awesome-jev
Frequently asked questions
What does the demo do?
It tracks a mood state that changes as you talk to it nicely or nastily.
Where can I try it?
At jev-demo.vercel.app.
Is the code available?
The listing does not say.
Related projects
- jev-chat-windows★ 802
Windows WeChat reply assistant: local offline OCR reads the chat, Jev judges intent and tension and ranks three drafted replies to fill in.
ProjectproductionPython Mangaba AI's local, calibrated typed-decision model for Portuguese text, trained to optimize the Brier score; proprietary since v5.
ProjectproductionPythonSimon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.
PluginproductionPythonOh My Pi coding agent (a Pi fork with IDE wiring) with an optional TypeSafe judgment provider for bounded decisions.
ProjectproductionRust- jev-arena★ 122
Side-by-side tool comparing Jev and DeepSeek on labelling the same comments for relevance, sentiment and intent, with replay and reports.
ProjectbetaTypeScript Agent Zero plugin adding a typesafe_query tool that asks Jev Choice, Noul and Score questions and shows probability cards in chat.
ProjectbetaPython