User repository on GitHub
LLM plugin for accessing Jev and other TypeSafe AI models
- Forks
- 2
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
LLM TypeSafe
LLM CLI plugin that exposes TypeSafe classification and scoring as a jev model with yes-or-no, category, and rubric-rating calls from shell or Python.
- Stars
- 26
- Language
- Python
- License
- APACHE-2.0
- Published by
- Community
- Author
- simonw
- Last verified
- Oct 2026
About this project
Use TypeSafe classification and scoring models with LLM. 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:
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- Adds a typesafe model alias with yes-or-no probability, multi-category choice with confidences, and rubric scoring.
- Shell flags control answer type, criteria text, JSON input mode, and saved reusable prompt templates.
- Python sync and async paths return parsed answers plus full provider response and usage metadata.
- Criteria need at least two named categories, or two to ten ordered rubric steps from lowest to highest.
Watch out
Text is never auto-parsed as JSON, arrays count as one input state, and score outputs measure rubric degree rather than yes probability. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
Pick noul for yes-or-no probability, choice for one-of-several categories, and score for rubric degree. Scores on a three-level rubric run fractionally across the range instead of reporting yes probability.
With input_format set to json, the whole prompt must parse as a JSON string, object, or array, with duplicate keys and non-finite numbers rejected. Otherwise input stays plain text.
Yes. Save a parameterized call as a template, then pipe new inputs through it. Standard fragments, stdin, key handling, and logging keep working through the normal model API.
Install the plugin, store the key with the CLI key command, then call the jev alias or use the model object in sync and async Python. Responses include probabilities plus full provider payload and usage.
It adds a model called typesafe/jev-latest with the alias jev. Install it with llm install llm-typesafe, then set a key with llm keys set typesafe.
Choice needs at least two category names with descriptions; a description may be null when the name alone is enough. Score needs 2 to 10 ordered descriptions from lowest to highest; with three levels scores run 0 to 2 and may be fractional.
A JSON object with type choice, the chosen option, a confidence, and a probability for every option, for example {"type":"choice","choice":"technical","confidence":0.97,"probabilities":{"technical":0.98,"other":0.02,"billing":0.0}}.
More Jev resources like this
34GitHub stars
Pure-HTTP automation for the TypeSafe register, magic-link login, onboarding, and API-key creation flow, with pluggable temp-mail backends, concurrent batch runs, and key verification exports.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
2951461586/Jev-Register-ToolPython
2951461586/Jev-Register-ToolPython36GitHub stars
Python toolkit plus 0.8B multimodal model that takes a message, document, or image and returns calibrated choice, yes/no, and score answers in one forward pass for local decision workloads.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
PsiACE/dohnutsPython
PsiACE/dohnutsPython39GitHub stars
Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
cclank/jevclipPython
cclank/jevclipPython30GitHub stars
Forkable weekday radar that asks Jev one yes-or-no question per interest over each new arXiv announcement and publishes a page plus RSS feed.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
Eliot5566/JEV-Paper-RadarPython
Eliot5566/JEV-Paper-RadarPython38GitHub stars
Async supervisory layer for Hermes Agent that locks Definitions of Done, proves mechanical criteria locally, and calls Jev only for unresolved semantic checks under a token budget.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
keeltrace/hermes-nervePython
keeltrace/hermes-nervePython15GitHub stars
Two-tier decision engine pairing a 22.6M-parameter MiniLM encoder on the Apple Neural Engine with the on-device Apple Foundation Model as fallback for uncertain inputs.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
kerryrm/systemANEPython
kerryrm/systemANEPythonFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.