Jev ecosystem projects — page 8

High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev. Rust streaming core, Parquet and JSONL I/O, typed Choice/Score/Noul judgments, speculative fan-out, 24.0 rows/sec measured.

Jev × socai for social media research on Instagram, TikTok, and LinkedIn—typed routing, real browser evidence, streamed posts, video capture, and cited reports.

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.

Train a Jev-like multimodal model by yourself. System One Model, now with vision.

jev-seo: Rust SEO and GEO CLI plus MCP server for coding agents: 50-rule audits, live crawls, GEO scores, rank drift, CI gates. MIT, zero subscription.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

Ruby client for decision models such as Typesafe Jev

Provider-neutral System One runtime for TypeScript and Pi

An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post

Route HTTP requests by meaning. A semantic router for Hono powered by Jev.

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev

Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.

TypeSafe decisions for Pi: batched evaluation tool, terminal playground, and typed API for extension authors

A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework.

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client

Turn any off-the-shelf LLM into a Jev -like decision layer

Two-stage JEV control of a Franka Panda in MuJoCo

A self-hosted API and web interface for Laya’s structured decision models, compatible with the TypeSafe Jev API format.

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

Use cultivar to test your Agent Skills and Docs by running them in sandboxes, and across different agents.