SsimotaBenchmarks & research

tenbin

MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code

Explore repository

How it uses Jev

A repository for using TypeSafe AI (System One API, model Jev) from a coding agent at design time . It has three parts.

Getting started

Prerequisites: Node.js 22 or later, a TypeSafe API key (https://console.typesafe.ai/settings/keys).

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to tenbin

Browse all
jev-mcp-server project preview

jev-mcp-server

Benchmarks & research
MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.
WMade bywangkuangkuang2
jev-x-kit project preview

jev-x-kit

Benchmarks & research
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.
KMade byKadihx2
typesafe-demo-mcp project preview

typesafe-demo-mcp

Agent tooling
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools
BMade bybestagentkits0
qwen-rlcd project preview

qwen-rlcd

Benchmarks & research
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B
SMade byshamazharikh4
jev-mcp project preview

jev-mcp

Agent tooling
MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents
RMade byrajasekharponakala2
jev-mcp (rashedInt32) project preview

jev-mcp (rashedInt32)

Agent tooling
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
RMade byrashedInt327
jevflow project preview

jevflow

Applications
Probabilistic AI decisions as composable backend primitives — typed judgments (noul/score/choice), deterministic thresholds, and explainable workflows. Powered by TypeSafe's Jev, provider-agnostic.
MMade byMawfyy9
commentcop project preview

commentcop

Applications
Put your code comments on trial. Powered by Jev.
NMade byntedvs1
n8n-nodes-typesafe-ai project preview

n8n-nodes-typesafe-ai

Integrations
n8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities
DMade byDomMonte0