Jev MCP Servers and Agent Skills

kerpopule/hermes-jev-skills

Bundle of skills that hand an agent's small decisions to Jev: model routing, skill selection, retrieval filtering, compaction, and computer use, with a routing dashboard. Works with Hermes, Claude Code, and Codex.

wuyoscar/jev-skill

Nine installable agent skills — triage, routing, code review, document and UI work — with a catalogue of scenarios to copy.

jkudish/jev-mcp

Proof-of-concept MCP server with ready-made tools for fact checking, prompt-injection detection, and semantic ranking.

itsmostafa/system-one-connector

MCP connector that gives Claude Code, Claude Desktop, Codex, Hermes and pi an evaluate tool, pointed at Jev or at an open System One model you host.

Devin-AXIS/jev-dsh-decision

Decision plugin for agent harnesses: Jev picks the tool, skill or owner and scores the output, while the agent keeps planning and execution. Ships for DeepSeek Harness and iPolloWork.

luobosibing2/dsh-jev-plugin

Eleven DeepSeek Harness judgments - skill and file selection, supervision, tool-output filtering, approval help - each configurable and all off by default. The main model still plans and answers.

ThinkFlowLab/system1-agents

Prebuilt agents whose decisions come from a System One model, Jev or an open one, covering browser use, computer use, robotics and games, with a scaffold for building your own.

dbreunig/building-with-jev-skill

Agent skill for writing programs that call Jev: question design, state structure, confidence thresholds, and diagnosing wrong answers.

aaddrick/building-with-typesafe-jev

Agent skill with a code sketch per project shape, and an eval harness that runs the same task with and without the skill and keeps every run's output in the repository.

UditAkhourii/quicksilver

Claude Code skill for the bulk judgement calls — which of these files, which of these log lines, which of these tickets — that otherwise get read one by one.

PerryLink/jevcore

Typed decisions for DeepSeek Harness and any other MCP host, also usable as a plain Node library.

charlesdove977/claude-x-jev

Claude Code skill and commands that hand sorting, checking, scoring and gating to Jev over OpenRouter, with presets for jobs such as email triage, plus an optional hook that, once switched on from shadow mode, lets Jev approve tool calls it is confident about.

TheoOliveira/pi-jev

Semantic tool routing and skill discovery for the Pi coding agent: Jev picks which inactive tools to activate for the prompt at hand.

burnigtm/jev-mcp

MCP server whose tools route the next step and decide whether a partner model is needed, for Cursor, Codex, and any MCP client.

shitianfang/jev-use

Claude Code, Codex and pi plugin that hands the agent steps needing no written output to Jev and leaves the prose to the LLM.

kenz1117/dsh-engram

DeepSeek Harness memory plugin built on the memory-palace layout - fixed locations as the index, routes that only grow - with cue-only spaced recall. Chinese.

FrancoisChastel/jev-code

MCP server giving Claude Code, Codex, Pi and OpenCode five typed tools - classify, check, score, rank, ask - with one request per tool call and the hosts it talks to written down in SECURITY.md.

DeepAleph/jevreel

MCP tools and a skill for searching video without embeddings: frames are tiled into labelled contact sheets, and Noul, Choice and Box questions on Jev 1.14 find, check and locate moments.

a2sys-ai/jevfetch

Web-page reader for coding agents, as a skill and CLI in place of WebFetch: it splits a page into blocks, asks Jev which ones answer the question, and returns those blocks verbatim with their heading paths.

kbhuw/jev-sift

MCP plugin that asks Jev which files, web pages, or text snippets are relevant to a query, so the agent reads selectively.

PyModel/jev-judge-mcp

MCP server that gives a coding agent eleven judgment tools backed by Jev, for the checks whose answers can be enumerated.

tacticocc/Jevbridge

ACP and MCP adapter that pairs Jev with any LLM agent, including Codex, Claude, Grok, and OpenCode, for typed decisions and computer use.

altryne/jevify

Agent skill for finding where Jev fits in an existing codebase, designing the typed questions, and measuring whether it helped.

grandamenium/jev-anything

Agent skill for designing, building, testing and tuning a bounded decision layer, with a client scaffold it writes for you.

TypeSafeAI/jev-harness

Research-stage proposal-review contract: an LLM proposes one action, four narrow questions are answered, and code produces evidence for a host to judge — it applies nothing itself. From the independent TypeSafeAI community organisation, which its README distinguishes from the official team.

safzanpirani/pi-jev-skill-picker

Takes Pi's generated skill catalogue out of the system prompt and puts a ranking tool in its place, so skills are pulled in on demand instead of carried in every request.

tomascupr/reelql

Claude skill and API that turns a video link into one typed JSON document: chapters, scenes, key moments, on-screen text and transcript.

madisonrickert/jev-permission-gate

Claude Code mod that answers auto mode's tool-call question with eight yes/no questions in one request, behind a shell-aware blocklist whose flags Jev can deny but never wave through.

AskTheWay/dsh-jev-interceptor

Judges every tool call and recalled message inside DeepSeek Harness before it runs.

PanAchy/jevvy

Plugins for coding agents, starting with one that auto-approves shell permission requests it judges harmless and passes everything uncertain to the normal flow.

brianhong-dev/omo-jev-plugin

Rates how well the next skill or tool fits the work an OmO or senpi agent is doing and passes back a short suggestion. It runs no tool itself and replaces no permission check. Korean.

Brainwires/jevwire

An MCP server, an embeddable decision library, and an escalate-only Claude Code plugin in one repository.

Protocol-Lattice/harness-router

Routes an agent's tool calls, as a hook on every call or a skill you invoke, with MCTS for multi-step decisions.

anpicasso/hermes-jev-approvals

Approvals provider for Hermes Agent: it judges shell commands and refuses every other task, registering no hooks.

AgriciDaniel/gatekeeper

Decides which agent or skill should take a request before the agent picks for itself; tool-neutral rulebooks, installed today as a Claude Code hook.

shimo4228/jev-skill-router

Claude Code hook that asks Jev which skill fits each prompt, in shadow or inject mode, published with the log of the week its author ran it and why they removed it. English and Japanese.

NiazMorshed2007/jcr

One tool that searches a nested capability tree and hands the agent only the documented commands and context a task needs.

gnipbao/jev-remix-cutter

Codex skill and Python CLI for local video remixes: shot and beat detection, Jev judgements on clips pinned to jev-1.13.0, and an originality and footage-licence report. Text goes to TypeSafe only after an explicit --allow-text-upload. Chinese docs.

Nanako0129/lorenzini

Claude Code skills that wait for CodeRabbit, Copilot or Codex to finish reviewing a pull request, then judge whether the verdict actually permits a merge.

ZephyrDeng/ego-jev

Agent skill that decides each DOM step from the page's candidate elements rather than spending an LLM turn on it.

utk2103/jev-studio

One pip install for experimenting: MCP tools for Choice, Noul and Score, prompt libraries and a slash command per cookbook recipe.

emirbartu/jev-for-all

Connects Jev to the harnesses agents already code in, from OpenCode to Hermes, so they can ask which skill to load, which tools a step needs, and where to go next in a browser.

DECRUX9812/typesafe-skill-router

Hermes Agent plugin that names the one skill worth loading before the model call. Off by default, injects nothing when nothing fits, and does not spend its second request when the first gate is not cleared.

Nyarlathoteppppp/pi-heed

Checks every side-effecting tool call the pi agent is about to make against what you actually asked for, before it runs.

HorusJiang/dsh-jev-tools

DeepSeek Harness plugin that judges tool output before it enters the context, screens fetched pages for injected instructions, and gates completion claims. Chinese.

duongvm57/paseo-slp-plugin

Supervisor, Lead and Peer roles for a team of Paseo coding agents, with opt-in Jev routing that records a verifiable receipt in shadow mode and binds it when armed. English and Vietnamese.

ismaelsoilet/jev-harness

Five semantic gates in front of a frontier agent, for trivial errors and doom loops, with a dependency-free local deterministic mode. English and Portuguese. One of three projects on this list called jev-harness.

cyberofficial/dsh-plugin-jev

Gives the agent in DeepSeek Harness's web GUI a jev_ask tool, so the model calls Jev itself when a decision needs a calibrated answer, with a per-chat usage chip. No licence file.

integrate-your-mind/jev-codex-plugin

Codex and Claude Code plugin whose MCP tools and hooks ask Jev to choose tools or strategies, diagnose failed commands and check completion claims against evidence; automatic consultation is off until enabled.

bgrablin/hermes-switchyard

Hermes Agent plugin that hands skill choice, reasoning effort, model recommendations and session re-ranking to Jev, through TypeSafe or OpenRouter.

BYK/jev-mcp

Eval-first MCP server that focuses on knowing whether Jev's answers can be trusted for your task.

pZacca/askjev

MCP server published on npm, with setup instructions for Claude Code, Claude Desktop, Cursor, and Codex.