Jev ecosystem projects — page 83

⚡ AgenticJev · 拾意 — 推荐智能体实验室。搜索 × 推荐 × 广告，Jev / MiniCPM / GPT / Claude 多模型决策与生成式组合对照。

Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines

An experimental Astra + Typesafe Jev Fallout: New Vegas project: read-only game observations, typed decisions, recording, and public commentary.

A curated guide to Jev, TypeSafe AI's System One decision model — selection advice, API-verified cookbooks, independent evaluations, and 100+ community. 中英双语

A community directory of open-source projects built on Jev, TypeSafe AI's System One model. Live index: jevusers.com

A crawler-maintained directory of projects built on Jev, TypeSafe AI's System One model. Daily GitHub + npm sweep, human-merged.

Experiments with TypeSafe/Jev semantic gates and a Semantic Operations Lab demo.

Bounded semantic routing with Jev and Poise. Rust, single-server, alpha.

Pareto-optimal menu picks on cost, macros, deliciousness, and reviews — with TypeSafe/Jev scoring and a fixed output schema.

Jev Bayes, No? Testing TypeSafe AI's Jev against Bayesian-optimal strategies, and testing if Jev can effectivly use Bayesian priors.

Real-time reflex layer for Claude Code guarded by TypeSafe's Jev System One model: calibrated probabilities in, deterministic allow/warn/block decisions out.

Clean your Google Other contacts with TypeSafe's Jev: Keep / Review / Remove

Cursor plugin that routes subagents with TypeSafe Jev and exposes Choice, Score, and Noul as MCP tools.

Open benchmark runtime for document-grounded decision models

Automated friction logs for online documentation, scored section by section with TypeSafe Jev

Ask your DuckDB tables questions in plain language. A DuckDB port of pg-jev, powered by TypeSafe's Jev.

⚖️ Judge git commits with Jev: is it breaking, does it deserve attention, and does its message tell the truth?

No project description available.

Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.

Semantic task routing for software development, powered by Jev.

Find where TypeSafe Jev fits your real workflows. An evidence-based audit skill for Claude Code, Codex, and compatible agents.

Does the cited source actually say it? A 42-claim benchmark: Jev (TypeSafe System One) against GPT-5.4, Claude Sonnet 5 and Gemini 3.1 Pro.

A benchmark for Jev's biases, built from people who differ in one attribute at a time.

Jev-style /v1/systemone API in front of any OpenAI-compatible LLM server (one-token logprob scoring, MIT)