Agent Tooling for Jev

Build and run agents you can see, understand and trust.

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

Unix like coding agent

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero runtime deps, SQLite, MCP. Benchmarked retrieval with an opt-in hosted TypeSafe Jev reranker.

Get FAR MORE done with FAR FEWER tokens 🔥

The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.

A staged code-review workflow and local dashboard built with TypeSafe Jev.

Software factory foreman based on TypeSafe's Jev model

a coding agent, rpc plugin, sub-agents, hashline edits, and mcp

Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

Give your Hermes agent the web as real sources, never a made-up answer — multi-provider search and extraction with an optional local, key-free DonSeTch option.

Route to the cheapest model in claude code for your task using jev-router

Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.

An mcp connector to evaluate anything fast and cheap. Give your AI agent direct access to typesafe ai's jev model and open weight models like laya

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 72 tok/s greedy median, 1M context, deterministic boots. Flash-Next 176B on one box. One command, everything pinned, and a local cockpit to drive it.

openworkbuddy — local-first AI office agent: turn requests into real files. Self-hosted, BYOK, MCP, Codex/Claude Code, executable short-drama canvas.

A lightweight Jev-powered router for models, tools, and subagents

LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.