Jev in production › SDKs and workflow integrations

llm-typesafe

Plugin for Simon Willison's LLM CLI and Python library that adds a jev model returning typed yes/no probabilities, category choices and rubric scores as JSON instead of text, with templates and stdin support.

Open on GitHub ↗

The source publishes no measured number.
Use
SDKs and workflow integrations
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
LLM CLI
Listed
2026-09-23
Found via
github
Repository
simonw/llm-typesafe
Stars
27
Forks
2
Last push
2026-09-22
Language
Python
License
Apache-2.0

The README opens with

This plugin adds a model called typesafe/jev-latest, with the alias jev.

You can add -o answertype noul, but that is the default if no answer type is specified. "Noul" means a yes/no answer (from "Bernoulli distribution"), and returns the probability of yes between 0 and 1.

Optional definitions can be supplied using -o criteria '...', like this:

Use an answer type of "choice" for an answer from one of several provided categories:

Supply at least two category names with descriptions; a description may be null when the name alone is sufficient.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sdks and workflow integrations