882 repositories with documented relationships and source evidence.
Nearly half the agent cost, with accuracy intact. Just enough tools is a DeepSeek Harness plugin that uses Jev to reveal tools and skills progressively. The main model starts with a clean planning step. Jev then selects which capabilities to add as the task unfolds.
DeepSeek Harness WSL plugin: TypeSafe Jev / OpenRouter System One (jev_ask / check / rank)
Go harness for Jev/Kev decision models: TypeSafe, Vercel AI Gateway, and in-process Kev via llama.cpp
decision-first data cleaning system powered by Jev
Local MCP server for TypeSafe Jev typed decisions, with Codex integration
A Codex skill that asks TypeSafe Jev through OpenRouter which model and reasoning effort to use
JEV Reasoning Navigator: Cognitive supervision, loop prevention, and anti-hallucination engine for autonomous LLM agents using TypeSafe AI
Claude Code plugin that routes skill selection and post-turn code judgment through TypeSafe Jev on OpenRouter
A JEV-gated semantic communication layer for parallel coding agents.
JevCore Agent — local coding harness (Jev decisions, Guard hard policy, MCP + CLI)
OpenCode plugin that routes per-request reasoning effort for agents via Jev (TypeSafe SystemOne) — cheap prompts stay cheap, hard ones get full reasoning
Check agent file changes against your project's written constraints, using TypeSafe AI's Jev decision model
Learning infrastructure for typed probabilistic decisions from System One models (Laya, and typed-decision providers you bring yourself).
Token-efficient agent memory for Claude Code and Codex, using TypeSafe Jev for typed decisions and a primary LLM for validation.
A plugin that lets you build reusable **solution signatures** for any classification or scoring problem, then run CSV, Excel, or text file datasets through the [TypeSafe Jev](https://docs.typesafe.ai) API and export structured results to Excel.
🧠 MCP server for TypeSafe's Jev model
Local-first task router for microservices, polyrepos, monorepos, and coding agents.
/whisper: a Claude Code skill that optimizes your prompt before it runs and gets better every time you correct it.
⚡ DataJev LLM → Analyze Jev → Continue / Switch / Verify / Stop System-1 control for System-2 data agents
One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback
A nutrition label for AI-written content: audits what AI agents say about data, blocks what doesn't hold up, and shows readers why. Powered by Jev.
Fast Memory is an agent memory system built with Jev + LLM.