Built with Open reimplementations
sarvam-jev
Generation-free typed decisions on Indic LLMs. An open Jev-style inference engine on sarvam-1: constrained logit readout instead of autoregressive JSON. Runs client-side in the browser.
61 ★ on GitHub
What it is
Generation-free typed decisions on Sarvam's Indic models.
The homepage listed on the repository, sarvam-jev.feynmanpi.com, puts it like this: Read typed decision probabilities out of an Indic model
Getting started
From the README:
uv sync # creates .venv from pyproject.toml + uv.lockWhere the decision sits
sarvam-jev runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.
How active it is
Created 2026-09-18, last pushed 2026-09-18, 61 stars and 11 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.