kev
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
kev launched on 17 September 2026. It ranked #98 on Daily Launch on 15 October 2026 with a Launch Score of 16, from +62 stars on 15 Oct on GitHub. It moved down 54 places from the day before.
What is kev?
Small Jev-like decision models you can train and run yourself. Kev is a family of small decision models built on Qwen3.5 and Qwen3.8 and based on the architecture described in Jev's Architecture Unmasked. You can use the pretrained weights or train your own. The API matches TypeSafe's System One, so you can point their Python SDK at your local server.
From its README on GitHub
kev is a repo by jaredpalmer on GitHub. It is written in Python and released under the Apache-2.0 license.
How to get kev
git clone https://github.com/jaredpalmer/kev.git && cd kev
uv sync --extra serve
uv run --extra serve python -m kev.serve --run jaredpalmer/kev-4b --port 8009From its README on GitHub
More steps and the source are in its repository on GitHub.