Agent tooling — page 8

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

SAP Commerce extension using TypeSafe's Jev to moderate product reviews and suggest product categories and classification attribute values: dry runs on your own data first, an audit record per decision. Plus a Claude Code skill.

DeepSeek Harness plugin for TypeSafe Jev: typed decisions, configurable guardrails, and Web UI result cards.

Confidence-gated incident routing with TypeSafe Jev

Jev-powered MCP tool routing for Codex

TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

Jev-scored context compaction for OpenAI Codex CLI — scores every tool call before compaction and restores critical tool outputs verbatim after it

Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback.

Jev (System One decision model) plugin suite for DeepSeek Harness (dsh)

Code-review gate for CI and coding agents: asks TypeSafe Jev small typed questions about functions, files, tests and docs, and reports findings with locations and probabilities

LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

DiffJury — TypeSafe Jev PR risk router + code review coach

Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

Architectural Moat: JIT-JEV Context OS — Epistemic runtime & JEV System 1 context gate for AI agents (L0 SQLite WAL <3ms, Epistemic Invariants I1–I10, CERN Zenodo DOI: 10.5281/zenodo.22649542)

Jev Auto Router (Jev Router): experimental per-call GPT model routing for Codex via TypeSafe Jev and a local Responses proxy, with independent task verification.

Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.

Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.

Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script

情緒測謊器：嘴上說「好」，心裡真的好嗎？用 TypeSafe Jev（System One 模型）透過 OpenRouter 即時判斷，並與一般 LLM 對照

Jev-scored context pruning for OpenCode: drops stale tool calls and truncates bulky results on the outgoing request — fail-open, cache-backed, configurable live. Port of fast-jev-compaction to the V2 context hook.

Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler