Jev ecosystem projects — page 64

Calibrated picks for Neovim, judged by TypeSafe Jev. First source: effect-error-pretty.nvim

Kade console is a bloomberg terminal type of analytical tool.

Delegation policy for Claude Code, cut down to what its own benchmark supports: two pinned roles, and a skill that argues against delegating by default.

a repo that helps you learn jev model.

A Magic Jev (8) Ball for pull requests.

Open MCP server to run TypeSafe Jev (System One) packs locally — Choice / Noul / Score for Cursor & agents

MinusPod Jev Proxy

Tools for stopping doom scrolling and engaging more productively on the web using TypeSafeAI's Jev Model

Verbatim context compaction for Oh My Pi (omp) using TypeSafe Jev decisions — port of joelhooks/pi-fast-jev-compaction

OMP / pi-coding-agent extensions that delegate acceptance gating and subagent routing to the Typesafe Jev decision API

TypeSafe Jev-powered intent gate for OpenCode: confirm intent before the agent dives into underspecified requests.

OpenCode plugin: trim long Bash output with TypeSafe Jev before the model sees it

Nudge your agent, when jev deems it so!

System-One control plane for Pi Coding Agent powered by TypeSafe Jev.

Analyze prompts with TypeSafe Jev before GitHub Copilot

Cost-aware PR review using TypeSafe Jev decisions before a generative reviewer.

A model-agnostic, Jev-first Responsible AI harness for assessing AI systems for prompt injection, secret/PII leakage, unsafe tool use, and policy bypass. Runs portable tests, captures evidence, scores risk with calibrated uncertainty, and routes serious or unclear findings to human review.

Fast, prefill-only decision model. Typed questions in, calibrated probabilities out, single forward pass with TypeSafe System One API. inspired from jev

Experimental: hand it a Salesforce org and a manual step. An LLM plans, Jev (TypeSafe) chooses every action, Playwright executes.

Steve

Wire a cheap LLM to TypeSafe Jev with one OpenRouter key

Provider-agnostic TypeScript SDK for decision models — typed answers with calibrated uncertainty, instead of text you have to parse. Pre-release, not on npm yet.