Jev ecosystem projects — page 62

INSTRUCT_JEV - TypeSafe AI Jev / System One instruction corpus (choice/noul/score), compiled by DeckerGUI. 119 rows. Mirrored on HuggingFace.

JEB: a System One-compatible decision model API. State + typed questions in, calibrated probabilities out, one forward pass.

A coding agent CLI where Jev (TypeSafe System One) or Laya decide what to do next and a configurable LLM does the work.

Mini benchmark of TypeSafe's jev-1.13 structured decision model (OpenRouter Decisions API) on labeled support-triage: noul/choice/score, consistency, cost, lessons learned

Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents.

Reproducible evaluation of TypeSafe Jev on all 58,492 BBQ questions: accuracy, stereotype bias, uncertainty, cost and latency.

Give any MCP-capable LLM harness an on-demand real-browser search tool (TypeSafe Jev) with per-run timing and cost tracking.

CI example using Jev to classify failed PR checks and return structured decisions with probabilities.

Zero-dependency TypeScript client for TypeSafe Jev (System One decision model) — OpenRouter, TypeSafe direct, and Vercel AI Gateway providers

Local, contract-compatible System One decision server (typed questions -> calibrated probabilities, zero generation). Independent reimplementation; not affiliated with TypeSafe.

Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.

Jev learns your repo's decision norms, then adversarially judges past decisions against them. Unix-style primitives (seed, expand, judge, verify, report, norms) with per-node typed judgments from typesafe-ai/jev.

TypeSafe Jev arcade

TypeSafe.ai Jev Go SDK

A safety boundary for AI-assisted Home Assistant decisions, with explicit policy checks and deterministic state verification.

MCP server exposing TypeSafe's Jev as a judge tool: typed judgments with calibrated probabilities, for any MCP client.

Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.

Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

Give your Jev language, i'm not finish now

Jev decides whether a batch of logs is worth acting on. Typed questions, confidence gates, nothing executed.

AI defect code suggestions for Non-Conformance Reports, powered by TypeSafe AI's Jev model

A vocabulary-driven TypeScript runtime for safe, stateful applications powered by TypeSafe AI Jev.