kyle-pena-nlp/jevchat

Turns Jev into a chatbot

Language modelsPython

3.1 Early signal Magnitude out of 10. Star growth looks organic. Data as of September 20, 2026.

About the project

An experimental chatbot that generates replies by asking the Jev model which symbol, word or hypothesis comes next; built for fun, not practical use.

Useful for

Chat interactively with the model via poetry run jevchat
Compare sampling strategies and alphabets using the bench command
Ask a single question from the CLI and watch the step-by-step symbol distribution

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

10 stars so far today, about 11 expected by the end of the day.
The repository is 0 days old and already has 11 stars.
Hacker News: “I turned Jev into a (lousy) chatbot” — 58 points, 3 h ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 11
Stars in a day: 11
Forks: 0
Issues and pull requests: 0
Watchers: 0
Language: Python
Created: September 20, 2026
Last push: September 20, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

I turned Jev into a (lousy) chatbot58 points, September 20, 2026

Spotted in

September 20, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/kyle-pena-nlp/jevchat.svg?lang=en)](https://gitnova.dev/en/r/kyle-pena-nlp/jevchat)

Similar projects

7.8
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.

Early signalLanguage modelsPython+1,350 stars in a day
7.5
bespokelabsai/nimble
Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition…

Early signalLanguage modelsPython+458 stars in a day
7.3
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).

Early signalLanguage modelsPython+304 stars in a day
7.1
higgsfield-ai/higgsfield
Fault-tolerant GPU orchestration and ML framework for distributed training of models with billions to trillions of parameters, including LLMs. Manages node access, experiment queueing, and GitHub Actions integration.

BreakoutLanguage modelsJupyter Notebook+302 stars in a day
7.1
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.

Early signalLanguage modelsPython+352 stars in a day
6.9
githubnext/localjev
A local TypeScript/Bun HTTP service implementing a Jev-compatible POST /v1/systemone API on top of an OpenAI-compatible Chat Completions endpoint (DiffusionGemma via oMLX). It acts as a bridge for typed decisions…

Early signalLanguage modelsTypeScript+112 stars in a day