Can I clone this and run the application now?

No. The digest states source code and assets will be added by the agency as it executes the build, so treat the repo as the build specification today.

How is this supposed to get built from just a spec?

Hand BUILD_PROMPT.md to a coding agent such as Claude Code, Codex, Cursor, or a human agency; it is described as the complete agency-ready specification.

How is this different from keyword job-board ranking?

Keyword ranking is the contrast: Apply OS ranks by stated goals, CV match, visa, location, and compensation fit, each with an attached confidence score.

Why use Jev instead of a chat model for job triage?

Jev returns typed yes/no, choice, and score answers with probabilities that code can branch on, which the digest calls the exact primitive for this pipeline.

What does Apply OS produce each day?

It ingests every job posting and recruiter message, scores each against your goals and CV with typed, calibrated Jev decisions, and lands 3 to 5 real high-fit opportunities on your desk each morning. Cover letters are drafted, guarded, and citation-checked before you send, and application status is tracked automatically.

What files does the repository actually contain today?

BUILD_PROMPT.md, the complete agency-ready specification, plus the README. Source code and assets are to be added by the agency as they execute the build, and the stated status is repository initialized, build in progress.

Which TypeSafe docs does the spec point builders to?

The README links the TypeSafe AI docs, the composite-scoring pattern for resume screening, the JavaScript SDK, and the confidence guide, which are the references a builder needs for typed decisions and confidence handling.

CommunityJev Models & Reimplementations

Apply OS

Career decision-engine spec that scores postings against goals and CV with Jev and drafts guarded, citation-checked cover letters.

See highlights

Open github.com

Stars: 0
Published by: Community
Author: ozzy2438
Last verified: Oct 2026

ozzy2438/apply-os

User repository on GitHub

View on GitHub

Apply OS — Personal career decision engine powered by TypeSafe AI (Jev). Ranks job postings, drafts applications, and automates the pipeline with typed, calibrated decisions. Agency-ready build spec included.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Personal career decision engine powered by TypeSafe AI (Jev). Apply OS ingests every job posting and recruiter message you receive, scores each one against your goals and CV with typed, calibrated decisions from Jev, and lands 3–5 real high-fit opportunities on your desk every morning. Cover letters are drafted, guarded, and citation-checked before you send them. Application status is tracked automatically.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Ranking

Used inJev for Software & DevTools

Highlights

Ingests postings and recruiter messages to score fit against goals, CV, and constraints.
Plans 3-5 high-fit opportunities per morning with drafted and citation-checked letters.
Centers on BUILD_PROMPT.md as the agency-ready end-to-end build specification.
Links TypeSafe docs, composite-scoring pattern, JavaScript SDK, and confidence guide.

Watch out

Specification only: the repository is initialized with BUILD_PROMPT.md and source is to be added by the agency as it builds. 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.

More Jev resources like this

Bud Decision Studio

107

Cross-platform desktop app and serving system for open Jev-like decision models. It runs laya, kev, Jev-Omni and others locally behind the Jev API at POST /v1/systemone, with a playground, versioned templates, decision history and a LoRA Train page.

Jev Models & Reimplementations#community#desktop-app#local-ai

Community

BudEcosystem/Bud-Decision-StudioHTML

system-one-foundation-models

Native Swift 6 package that evaluates @Generable structs and enums through System One decision models in 15-150 ms, with on-device Laya, self-hosted laya-serve, and TypeSafe Jev cloud backends.

Jev Models & Reimplementations#community#github

Community

peterfriese/system-one-foundation-modelsSwift

Bekko System One

Independent training toolkit and open weights for System One decision models in the same category as Jev: 17M, 68M, and 400M models answering Choice, Noul, Score, and reranking questions, with Python and ONNX inference and a documented generalization gap to Jev 1.13 on the project's S1MB benchmark.

Jev Models & Reimplementations#community#decision-models#onnx

Community

hotchpotch/bekko-system-onePython

gut

Python helper that turns judgment calls into one-liners like likely, classify and rate, defaulting to Jev while also running on local or OpenAI-compatible backends.

Jev Models & Reimplementations#community#github

Community

Kungie/gutPython

kev-onnx

Self-hosted CPU-only server that speaks the /v1/systemone wire format for the KEV decision model, packaged as one container with ONNX Runtime and a health check.

Jev Models & Reimplementations#community#github

Community

aleskxyz/kev-onnxPython

laya-jev-compatible-server

Laya multilingual server exposing POST /v1/systemone and GET /v1/models for noul, choice and score questions, usable with the official TypeSafe SDK.

Jev Models & Reimplementations#community#github

Community

exfly/laya-jev-compatible-serverPython

From the Jev guides

Original write-ups on what this entry is for.

Multimodal Decision Models: What Clef and d1 Change

Oct 12, 2026

Jev takes text only; Clef-omni adds image, audio, and video input and Liquid d1 adds images, each keeping the same typed-answer shape. Where that matters, where it does not, and the costs the vendors underplay.

Jev Models & Reimplementations#multimodal#open-models#decision-model

Read article

The Decision-Model Price War

Oct 11, 2026

One model in September, a dozen by October. Clef, Liquid d1, Perplexity, and OpenAI all ship the same typed-answer shape now. How to read the rival benchmarks and pick on your own task.

Jev Models & Reimplementations#decision-model#benchmarks#pricing

Read article

What Is Actually on Hugging Face

Oct 8, 2026

Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.

Jev Models & Reimplementations#open-models#hugging-face#local

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai