떠 있는 채팅 패널이 의도, 위험, 답장 후보를 보여주며 사용자가 복사하거나 입력창에 넣을 수 있습니다. macOS 13 이상의 Apple Silicon Mac을 사용합니다. 화면 캡처로 읽을 때는 화면 기록 권한을, 텍스트 인터페이스로 읽거나 입력할 때는 손쉬운 사용 권한을 주고 설정에서 판단·생성 제공자를 선택합니다.
콘텐츠 및 글쓰기
생성 콘텐츠 계획, 평가, 개선
87 개 프로젝트 · 모든 프로젝트 →
305
문서를 추출해 Qdrant에 색인하고 개요를 계획한 뒤 로컬 자료에서 각 절을 조사합니다. Jev가 검색 조각을 판단·재정렬하고 부족한 근거를 평가합니다. 별도 LLM이 계획, 질의, 작성을 맡고 Python이 재시도를 제어합니다.
165
Build software like writing a book
A skill for writing and improving programs that call Jev, TypeSafe's System One model
33
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
29
A Document OCR Router to help route pages based on content.
AI summaries of Signal group content - text, images, links, voices. Runnable locally through ollama.
8
PowerShell decisions with TypeSafe AI's Jev model: https://typesafe.ai/blog/introducing-system-one-models-and-jev
Grade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.
Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy.
6
Self-hosted Jev decision workbench and Feishu bot: automatic choices, probabilities, and experimental word/character writing.
Explore real-world use cases and projects built with TypeSafe AI's Jev: content moderation, AI agents, model routing, and semantic search. Curated by SeeAPI.
A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally.
Agent Skill: harvest links from newsletter emails into Raindrop.io with the author editorial context attached - Gmail read-only, three-layer dedup, zero-context library compare
3
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
Content-aware PII redaction enforced in Neon Postgres: a redact() SQL function reveals or seals each field by your role.
Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.
3
next-generation decentralized voice recording platform that transforms how we capture, organize, and share audio content. Built as a comprehensive three-app ecosystem showcasing different Starknet integration approaches
An open-source, AI-powered resume builder designed to craft high-impact resumes. Features smart content enhancement using the STAR method, instant PDF previews, and seamless export. Built with Django, Htmx, OpenAI, and WeasyPrint.
Find out which qualities of your writing actually predict engagement. Rates every post you have published against a pre-registered rubric using Jev's calibrated judgments, then tests those ratings against your real engagement numbers. Refuses to report findings your sample cannot support.
Experimental: live X draft viral scorer powered by TypeSafe Jev
Jev-trading is a desktop application that combines the ultra-fast neural network model Jev (by TypeSafe AI) with an intuitive visual interface. We've created a platform where the power of algorithmic trading is accessible without writing a single line of code, messing with Python scripts, or configuring servers in the terminal.
Evaluate content for slop and guide revisions with 15 TypeSafe Jev scores. Not an AI-authorship detector.
Agent skill for writing programs with Laya and laya-cli — local typed decisions (Choice/Score/Noul), port of building-with-jev-skill to Laya