DigestAI news desk

Cut through the AI noise.

Agents & Tools1 min read

Simon Willison releases llm-typesafe plugin for TypeSafe AI's Jev model

Simon Willison announced a new plugin called llm-typesafe version 0.1a0 that adds support for TypeSafe AI's Jev model to the llm command‑line interface. The plugin is installed with llm install llm-typesafe and requires an API key that can be set using llm keys set typesafe.

1 source

Key points

  • The llm-typesafe 0.1a0 plugin adds support for TypeSafe AI's Jev model to the llm command‑line tool.
  • Installation uses `llm install llm-typesafe` and requires setting a TypeSafe API key via `llm keys set typesafe`.
  • The plugin can return yes/no, choice, or scoring answers, e.g., a yes/no request returned `{"type":"noul","noul":0.99}`.

The tool lets users ask yes/no questions, choice questions, or scoring questions to the Jev model. For example, a yes/no request returns a JSON object like {"type": "noul", "noul": 0.99}. More complex prompts can specify answer types and criteria, enabling structured classification of messages or reports directly from the command line.

Model page: Jev →

The story so far

6 episodes →
  1. Simon Willison releases llm-typesafe plugin for TypeSafe AI's Jev modelthis story
Full story from Simon Willison · by Simon WillisonOpen source ↗

llm-typesafe 0.1a0

Simon Willison · 22 September 2026

Loading the full article…

This text was published by Simon Willison and written by Simon Willison. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories