Jev Gamecast
CSV-to-dashboard app that charts columns automatically and optionally has Jev read every row for insights columns cannot answer.
Overview
The repository behind this entry, titled Jev Data Analysis in its README, turns a small CSV into a presentation-ready dashboard. It profiles every column, picks fitting charts and writes a headline for each. Optionally, Jev reads every row to find insights the columns cannot answer on their own. A list summary describes an earlier framing as Jev Gamecast, a replay-first app asking Jev typed questions about live sports data, and a football demo remains.
Built-in demos (the 2018 Central Park Squirrel Census and an illustrative football dataset that uses rules, not Jev predictions) run fully in the browser with no credentials. With the live backend, uploads are stored, shareable and public, so only non-sensitive data should be used; intake is capped at 5 MB, 5,000 rows and 100 columns, and URL fetches are hardened against private destinations. Questions the columns already answer are refused before any paid call, and paid analysis only starts on an explicit click.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this row show the pattern asked about?(inferred) | — |
| Choice | Which category does this row's free text fall into?(inferred) | — |
How it works
- Drop a CSV or pick a demo
- Profile columns and chart them in the browser
- Optionally click Analyze to have Jev read each row
- Show insights and share results
Strengths
- Useful dashboards without any model call
- Refuses paid calls for questions columns already answer
- Hardened URL intake
Caveats
- Stored uploads are public
- Name and description differ between list and README
Getting started
`npm ci && npm run dev`, then open /demo/squirrels or /demo/football.At a glance
- Type
- App
- Status
- beta
- Language
- TypeScript
- Runtime
- Vite web app with Convex backend
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data.
hellogumbo/awesome-jev
Frequently asked questions
When does Jev run?
Only when you explicitly start analysis of a stored dataset.
Are uploads private?
No, stored uploads and results are public.
Do the demos call Jev?
No, they run in the browser without provider requests.
Related projects
dbt package whose macros run Jev Choice, Noul and Score over SQL values in DuckDB and ClickHouse models.
ProjectbetaSQL (Jinja)DuckDB extension that asks Jev about every row in SQL and returns answers as ENUM, DOUBLE or STRUCT columns.
PluginbetaC++Python and Node library that classifies Hugging Face dataset rows on typed Choice, Score and Noul dimensions using Jev.
ProjectbetaPython, TypeScriptCodex plugin for batch labelling JSONL records with Jev under custom policies, with Codex reviewing uncertain labels.
MCP serverbetaTypeScriptMoves a coding agent's bulk semantic judgments (triage, tagging, routing) to Jev; an A/B reports 78% fewer tokens at similar accuracy.
ProjectbetaPythonGoogle Sheets custom functions JEV_IF, JEV_PROB, JEV_CHOICE and JEV_SCORE that classify, tag and score cells with Jev.
ProjectbetaJavaScript