Jev ecosystem projects — page 16

pre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt

Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev

Pi extension: verbatim context compaction with TypeSafe Jev decisions

Jev-assisted file retrieval and request caching for faster Pi workflows

在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。

Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.

TypeSafe Jev as the pi coding agent's quiet decision layer

Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

A small, extensible decision-to-action harness for TypeSafe Jev

iPhone 键盘版：一个自定义键盘打通所有聊天 App——长按复制对方消息，键盘上出意图、风险与候选回复，点一下进输入框。只读剪贴板，源码形式（需自行用 Xcode 编译安装）。

打っている言葉が日本語か英語かをJevに聞いて、Macの入力モードを切り替える道具。個人利用のみ。

80+ composable TypeScript recipes powered by Jev for AI agents, retrieval, answer verification, and conversation workflows.

System One judgments (noul/choice/score) from any LLM in one prefill — a Rust, Jev-compatible /v1/systemone engine

Fast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.

使用 TypeSafe Jev 审查 Skill 与 MCP 可疑行为 | Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps

ALGAL is a new take on the agent graph: a language and runtime for agentic program evolution.

A curated list of projects, integrations, and resources for Jev, TypeSafe AI's System One model.

Typed decisions from the shell: an unofficial stdlib-Python CLI and Agent Skill for TypeSafe's Jev model, via the TypeSafe API (default) or OpenRouter. Yes/no, choice and ordinal scores with calibrated probabilities, semantic grep and batch mode.

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.

A minimal permission gate for Pi in the style of Claude Code's auto mode