Jev ecosystem projects — page 70

Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets

Typesafe/Jev public X demo

An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.

TypeSafe's Jev model plays Snake live in the browser, with a headless eval and a self-improvement loop

Uses typeful jev, zero sync to pull and sync large repositories for issue triage

Let Jev (TypeSafeAI) solve 2048

Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.

Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)

MAGI system (Neon Genesis Evangelion) recreated with Jev, TypeSafe AI's System One model. 3 sages deliberate your question.

Description: Reproducible experiments for reliable LLM-to-MCP tool discovery, initialization, and calls using FastMCP and mock APIs.

Metis: automatic GitHub issue triage powered by TypeSafe AI Jev. A reusable GitHub Action.

Mr. Secret — blurs secrets & PII on any page using TypeSafe AI Jev

Your agent can't ask people what they think. nxk gives it a crowd to ask.

Experimental shadow-only watchdog for OMP using TypeSafe Jev. Records verification and tool-action instruction checks without steering the agent.

TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent

Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.

TypeSafe ranking, classification, retrieval and structured-decision tools for Pi coding agents

Pi extension that classifies each prompt with TypeSafe's Jev and routes it to the best model you're logged into.

Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.

I tortured Jev into being a RISC-V CPU.

Snake controlled by parallel Jev assessments, with one API call per game tick.

Evidence-backed code review for AI coding agents, powered by Jev.

Unofficial CLI + Python estimator of tokens, cost and context limits for TypeSafe (System One / Jev) API requests. Not affiliated with TypeSafe.