Skip to content

JEVChess — vamsi243

Minimal Chess.com-styled blitz and bullet chess app where Jev scores legal candidate moves in one parallel pass and reports confidence.

Stars
0
Language
HTML
Published by
Community
Author
vamsi243
Last verified
Oct 2026

vamsi243/JEVChess

User repository on GitHub

View on GitHub

JEVChess is an elegant, minimal chess platform designed around the chess.com aesthetic, It delivers rapid tactical responses using TypeSafe AI's **Jev** System-One model and heuristic fallback evaluation, without requiring any external database.

Forks
0
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

This is one of several Jev listings for the same project. The canonical entry is Jevchess — choxos.

About this project

JEVChess is an elegant, minimal chess platform designed around the authentic Chess.com aesthetic (#2c2b29 background, #4e7837 green squares, #ffffff white squares). It delivers rapid tactical responses using TypeSafe AI's Jev System-One model and heuristic fallback evaluation, without requiring any external database. All standard piece movements, captures, checks, checkmates, stalemates, and pawn promotions (auto-promotes to Queen for blitz speed) are strictly enforced.

Quoted from the project's README. Read the full README.

Highlights

  • 3-minute blitz, 1-minute bullet, and 5-minute rapid clocks with mandatory per-user match logging.
  • Single-pass Jev evaluation of legal moves with confidence, backed by heuristic fallback scoring.
  • Zero-framework vanilla UI with bundled chess rules engine and three backends: Python, Node, and Vercel.
  • REST endpoints for connectivity test, move selection, game saving, and per-user log fetch.

Watch out

Move quality is blitz-reflex heuristics plus Jev confidence, not deep search; expect tactical play, not engine-strength chess. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

3GitHub stars
Rubric-based eval harness that judges LLM and agent outputs with Jev through the Vercel AI Gateway, answering all rubrics for a case in one round trip.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Eleven-level Jev course from hello-world to a ticket-triage capstone, pairing short lessons with runnable scripts against the live API and using LiteLLM so the writing half works with any provider.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Wire-compatible Jev re-implementation reading typed decisions from an LLM's next-token logits, plus a reproducible JevBench-based comparison of that approach against Jev on identical items.
Jev Benchmarks & Evaluations#community#github
1GitHub stars
Deliberately overengineered TypeScript package that asks Jev whether an integer is odd, with ESM and CommonJS builds, typed answers, and token and timing receipts.
Jev Benchmarks & Evaluations#community#github
Native Apple Silicon harness comparing local decision models through one decision interface, running models serially and emitting an offline dashboard with latency and accuracy.
Jev Benchmarks & Evaluations#community#github
Local demo that runs Jev and Gemini in parallel over synthetic transactions, comparing decision, latency, tokens, and audit record.
Jev Benchmarks & Evaluations#community#github
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai