Jev ecosystem projects — page 33

Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces.

Typed model routing for OpenClaw agents, powered by TypeSafe Jev

Open-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review

Context compaction for Hermes sessions that never summarises: every tool call is scored by TypeSafe's Jev model, stale calls are dropped, everything kept stays verbatim.

Experiments on Jev’s probability calibration, uncertainty reporting, and forecast probability preservation.

open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Windsurf, & Claude Code

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev

弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。

Idiomatic Java SDK for TypeSafe AI Jev System One decision engine

Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.

Chess, Connect Four, and a decision model. Play Jev or watch Jev play itself.

Async-first Rust SDK for the TypeSafe AI API

A typed Python framework for controlling Android over ADB with Jev.

Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay

Input moderation for Mastra agents on TypeSafe Jev — one file

TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing

Agent Skill: harvest links from newsletter emails into Raindrop.io with the author editorial context attached - Gmail read-only, three-layer dedup, zero-context library compare

Plugin for oh-my-pi that uses Typesafe Jev API to classify tool calls as safe/unsafe/ask

Verbatim context pruning for the pi coding agent, scored by TypeSafe Jev: stale tool calls and results are dropped or truncated, everything kept stays verbatim.

Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.

A Demo of using JEV to classify various attributes of a book, and present that to the reader to augment the reading experience

A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent

Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model