MCP servers and agent skills with decision models

Claude Code plugin and Python CLI that hands judgments repeated over many items to Jev, with redaction, rate limits and a pilot run.

Standard-library MCP server giving Codex advisory Jev tools for role and resource selection, with local validation and 85 offline tests.

Composable Python toolkit for Jev: question builders, confidence gates, batch evaluator, calibration, CLI, MCP server and agent skill.

Local MCP server that lets an agent delegate a decision to Jev and get a recommended choice with percentages.

Fork of fast-jev-compaction adding env-configurable endpoints, a CLI, an MCP server and a Devin post-compaction restore hook.

Library, CLI and MCP server where an LLM states each step's outcome and Jev decides element, action, value and done/blocked/irreversible.

Native Bend executable that owns agent-launched processes and logs, and asks Jev a typed question only when told to.

npm CLI that screens large agent tool outputs with Jev, returning compact typed decisions and IDs while originals stay recoverable.

Governance proxy between Jev or local Laya and agents that turns probabilities into allow, ask, deny, keep, truncate or drop actions.

Unofficial dependency-free Go SDK and interactive CLI for Jev via TypeSafe or Vercel AI Gateway, with an agent skill.

Per-turn router: one ~350 ms Jev call picks model tier, effort, tools and skill, with a hard deadline and regex fallback.

Python MCP server wrapping Jev as classify, score, check, match and screen tools with confidence on every answer.

Local MCP server putting Jev in the coding loop: route next steps, pick prepared tool calls, review patches and verify claims.

Node MCP server with a dozen fail-closed Jev judgment tools: verify, screen, find, rerank, classify, extract, review and gate.

Claude Code, Codex and pi plugin that hands non-writing agent steps to Jev and escalates writing or unsure steps to the LLM.

MCP server, CLI and Claude Code skill with Choice, Score and Noul primitives and a confidence gatekeeper, hosted or offline.

Zero-dependency Node library with MCP and ACP adapters adding Jev decisions and gated computer use beside any LLM agent.

Semantic SQL for vanilla Postgres: jev() filters, jev_prob sorts and jev_choice groups are judged by Jev on rows after plain SQL runs.

Chooses the model tier, skills and MCP servers for each coding-agent session with two Jev requests, then launches Claude Code or Codex.

Evidence gate for RAG: a System One model judges whether retrieved excerpts support an answer before the LLM is allowed to speak.

Python decision gateway and stdio MCP server exposing Jev via OpenRouter's alpha Decisions endpoint to Claude Code, Codex and Cursor.

Agent skill and CLI that converts plain requirements, LLM prompts or prompt-calling code into a typed Jev request and runnable script.

Stdlib-only Python CLI plus agent skill for asking System One typed Choice, Score and Noul questions from the shell.

Go CLI and MCP connector exposing an evaluate tool for Jev and other System One models to Claude Code, Claude Desktop, Codex, Hermes and pi.

MCP gateway that trims noisy tool output and offers task classification and review advice, splitting work between local Laya and Jev.

Design-phase proposals for verbatim, Jev-guided context compaction in Kimi Code CLI via a forked mutating PreCompact hook.

Unofficial dependency-free .NET port of the TypeSafe JS SDK v0.6.0, accompanying blog posts including an MCP server.

Reproducible bake-off of Playwright CLI alone, CLI plus Jev, and Playwright MCP on fuzzy browser goals, with honest results.

Accenture thought piece and site on stack migration with Google Cloud, placing Jev as the System 1 layer that routes, classifies and gates.

Unofficial Jev operator lab: offline-first FastAPI app with primitives playground, cost lab, pattern pages and a TypeScript harness.