# kyle-pena-nlp/jevchat > An experimental chatbot that generates replies by asking the Jev model which symbol, word or hypothesis comes next; built for fun, not practical use. - Magnitude: 0.1 out of 10 — Quiet - Stars: 96 total · +0 stars measured 2026-10-07, 00:29–18:13 UTC, ≈ 0 by evening - Star trust: star growth looks organic - Category: Language models · Language: Python · Created: 2026-09-20 · Last push: 2026-09-20 - GitHub: https://github.com/kyle-pena-nlp/jevchat · Page: https://gitnova.dev/en/r/kyle-pena-nlp/jevchat ## 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 ## How to get started ```sh poetry install ``` Copied as is from the “setup” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/kyle-pena-nlp/jevchat#readme ## Why it’s here - Star-counter measurements on 2026-10-07 (UTC), 00:29–18:13: 96 → 96 stars (+0). This is the change over that interval. - The repository is 17 days old and already has 96 stars. - Hacker News: “I turned Jev into a (lousy) chatbot” — 177 points, 17 days ago. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 5 - Issues and pull requests: 0 - Watchers: 0 - Average over the last week: 0 per day - Usual pace: 4 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-24 1.5, 09-25 1.1, 09-26 0.7, 09-27 0.6, 09-28 0.8, 09-29 0.8, 09-30 0.8, 10-01 0.6, 10-02 0.2, 10-03 0.2, 10-04 0.2, 10-05 0.4, 10-06 0.5, 10-07 0.1 ## Hacker News - I turned Jev into a (lousy) chatbot — 177 points, 50 comments: https://news.ycombinator.com/item?id=49778162 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-07 18:14 UTC, updated every 30 minutes.