How fast LiQiiiii/Jeva 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
Oct 13 – Oct 23, 2026
Stars +88in 11 days
051015
15
Forks +8in 11 days
012
2
Merged PRs 0in 11 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Oct 13Oct 15Oct 17Oct 19Oct 21Oct 23
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
Day
Stars gained
Forks gained
Merged PRs
Tue, Oct 13, 2026
+0
+0
0
Wed, Oct 14, 2026
+4
+1
0
Thu, Oct 15, 2026
+10
+2
0
Fri, Oct 16, 2026
+7
+2
0
Sat, Oct 17, 2026
+5
+0
0
Sun, Oct 18, 2026
+15
+1
0
Mon, Oct 19, 2026
+10
+1
0
Tue, Oct 20, 2026
+9
+0
0
Wed, Oct 21, 2026
+12
+1
0
Thu, Oct 22, 2026
+11
+0
0
Fri, Oct 23, 2026
+5
+0
0
Total
+88
+8
0
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
1 post
10/ If you run agent routers or tool registries over a persistent catalog, Jeva's atomic option memory removes ordering bias and avoids re-encoding known tools. I think combining this symmetric mixer…
Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.
