Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

Zefan-Cai/Open-Jev

Visit GitHub
Python
443
65
1 contributors
MIT License
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Zefan-Cai/Open-Jev is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 20 – Nov 5, 2026

Stars +437 in 47 days

050100150
118

Forks +65 in 47 days

051015
12

Merged PRs 46 in 47 days

0102030
23

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 20Sep 26Oct 2Oct 8Oct 14Oct 20Oct 26Nov 1
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+81+70
Tue, Sep 22, 2026+118+120
Wed, Sep 23, 2026+84+82
Thu, Sep 24, 2026+29+50
Fri, Sep 25, 2026+16+50
Sat, Sep 26, 2026+6+50
Sun, Sep 27, 2026+8+50
Mon, Sep 28, 2026+12+30
Tue, Sep 29, 2026+10+00
Wed, Sep 30, 2026+7+20
Thu, Oct 1, 2026+7+00
Fri, Oct 2, 2026+2+010
Sat, Oct 3, 2026+3+023
Sun, Oct 4, 2026+1+011
Mon, Oct 5, 2026+2+00
Tue, Oct 6, 2026+1+20
Wed, Oct 7, 2026+1+10
Thu, Oct 8, 2026+3+10
Fri, Oct 9, 2026+5+00
Sat, Oct 10, 2026+0+10
Sun, Oct 11, 2026+1+00
Mon, Oct 12, 2026+5+20
Tue, Oct 13, 2026+4+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+4+20
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+2+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+1+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+2+00
Thu, Oct 22, 2026+4+00
Fri, Oct 23, 2026+2+10
Sat, Oct 24, 2026+2+00
Sun, Oct 25, 2026+2+00
Mon, Oct 26, 2026+4+00
Tue, Oct 27, 2026+0+10
Wed, Oct 28, 2026+2+00
Thu, Oct 29, 2026+0+00
Fri, Oct 30, 2026+1+00
Sat, Oct 31, 2026+0+00
Sun, Nov 1, 2026+0+10
Mon, Nov 2, 2026+2+10
Tue, Nov 3, 2026+2+00
Wed, Nov 4, 2026+1+00
Thu, Nov 5, 2026+0+00
Total+437+6546
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Sep 233 posts

    • Don't let a pretty preview make the decision. The preview says record_A. The action targets record_B. Open-Jev-27B-v1.1 catches the mismatch in this case. Two real predictions. Seven choices. Edited…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

    • Give your spreadsheet a decision button. Paste feedback or upload a CSV. Define labels: bug / refund / feature request. Review predictions. Download the results. Try the browser workbench (released…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

    • JevBench public 231 only (not full 534): 27B 197/231 (85.28%), Hard 80/111 (72.07%). Released 2B/9B: 150/231, 179/231. Jev: 200/231, Hard 81/111; still 3/1 ahead. New 2B training stopped; new 9B not…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

  2. Sep 212 posts3 posts

    • 7/9 Open-Jev ran on one H100 over loopback HTTP, cache off, candidate batch 1. Hosted models used HTTPS. Full-response timing includes validation; concurrency 1, no retries. Different hardware,…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

    • 8/9 All 231 planned tasks per model remain in the denominator. Saved-response replay, request accounting and model identity audits passed. Full protocol, per-tier scores, calibration metrics and…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

    • 12/13 Jev: 108/873 requests failed our strict probability-mass check; 66 queries score zero in the primary metric. Predeclared scalar-only analysis: .7282 / .7157, with no probability…

      Read full on X, posted by @Zefan_Cai

      @Zefan_Cai · x.com

You might also like

Repositories close to Zefan-Cai/Open-Jev
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

allebee/jevk5

Python

JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.

16014

kraayenjon/awesome-jev

A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.

20448

valentynkit/awesome-jev-typesafe

JavaScript

Typed decisions with TypeSafe's Jev, the first System One model

18862

zhengxuyu/litjev

Python

Turn any off-the-shelf LLM into a Jev -like decision layer

479

ikermoel/open-alternative-jev

Python

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

7614

alanhuangyoo/OpenJev

Python

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

704

nokia-applied-research/AnyJev

Python

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

1.6k186

j-geuter/Jeff

Python

Repository for serving models from the Jeff family

273

Amal-David/awesome-jev

Python

Jev demos, projects, SDKs and skills, with source links and a curated X gallery.

24428