Jev ecosystem projects — page 42

A curated list of what people built with Jev

DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.

Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out

Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

Jev adapter for Mellea

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers.

Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.

A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.

PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.

Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each

We ask Jev, TypeSafe AI's System One model, whether AI should kill us all. Every ten minutes. Using the actual headlines.

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

Route models and tools with TypeSafe

Swift SDK for TypeSafe AI

.NET SDK for the TypeSafe AI platform

Run AI coding agents in parallel, each in its own git worktree. Desktop app for Linux, macOS and Windows (Tauri + Rust).

Can we run something like Jev on a 3090 at home?