See what Jev can actually build.
Jev is TypeSafe AI's agent model. Every project below is pulled from X and GitHub, verified as a genuine Jev build, and tagged by category.
"Verified" means it passed our automated eligibility check — not that every claim in a project's own description has been independently fact-checked. How this works.
kitze/skillboxTypeScript — Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

yonatangross/orchestkitTypeScript — OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.

Python — A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
kyotofin/tax-doc-classifierTypeScript — Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.

iammrduncan/typesafe-ai-benchmarkTypeScript — This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.

TypeScript — Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.

TypeScript — Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
TheoLeeCJ/SemIfPython — Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

Go — mcp connector to give your AI agent direct access to typesafe ai's jev model
kitze/unclutterTypeScript — WXT browser extension: Jev-powered page clutter removal with reusable template rules.

OpenByteInc/QuantDingerPython — Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.
Python — Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
Python — Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

Devin-AXIS/jev-dsh-decisionJavaScript — Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。

vercel-labs/ai-cliTypeScript — Developer tooling: Vercel Labs CLI that can run Jev as the evaluation model for its `evaluate` command.

Python — Build calibrated AI Functions from human feedback using Jev and GEPA.

JavaScript — A playable Three.js driving simulator with Jev-powered autopilot







