Jev ecosystem projects — page 19

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.

Local Context Compiler (lcc): clean, dedupe and compact prompt context before it reaches the model, then report every block dropped, the cache tokens a pass invalidates and when pruning pays off. Runs offline with a local 1K decision model. MIT, no API key, zero telemetry.

DataFusion SQL functions for typed judgments. TypeSafe is one server.

Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.06/day, fork and go.

Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.

Open-source System One decision engine. Typed choice / score / noul with calibrated probabilities. Self-host with Ollama or any OpenAI-compatible model. Apache-2.0.

Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4s typed decision per DOM step instead of an LLM turn. Agent skill for ego lite.

把对双休的支持，带进每一次购物。逛淘宝、京东时，JEV 实时猜测商品背后的工作制，疑似非双休直接盖上 PASS。原页生效，边逛边选。

Unofficial Go client for the TypeSafe AI System One API (Jev) — typed questions in, calibrated answers out.

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly.

Use local and hosted classifiers aka decision models aka Jev-like models, all through a single TypeSafe API

An F1 racing game where TypeSafe's Jev picks the racing line and the pedals, and learns each corner's limit between laps

Luce: a recipe for calibrated decision models — a sentence about your task in, a small model that answers typed questions with honest probabilities out (init → synth → train → eval → serve)

Fast, typed browser automation powered by Jev and Playwright

Fast zero-shot and few-shot LLM routing powered by Jev.

An open-source, model-agnostic decision router for Claude Code and Codex.

turn any llama-server into a jev system one endpoint

Fast, drop-in multilingual profanity and toxicity screener for Node.js, powered by System 1 models like TypeSafe AI Jev and Laya. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.

Run a JSON Schema through TypeSafe's Jev API, and get JSON back.

NanoJev Snake Arena: 1v4 human-vs-AI battleship + 100-agent swarm simulator. Local demo of Jev System-One model (open-source mini replica).

Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.

Jev Playground