Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
snifftest
SkillsA prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
git clone https://github.com/DanRWilloughby/snifftest.git -
loki
SkillsThe agent that evolves with you 𖤍
git clone https://github.com/wundercorp/loki.git -
JevFlow
SkillsA Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.
git clone https://github.com/Parth1811/JevFlow.git -
jevgrep
MCP serversJev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
git clone https://github.com/nassim-arifette/jevgrep.git -
mu
Agents & frameworksmu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
git clone https://github.com/qybaihe/mu.git -
jev-browser
MCP serversBrowser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
git clone https://github.com/Ying-Kai-Liao/jev-browser.git -
Decidealot
MCP serversLocal Laya and Von typed decisions over TypeSafe-compatible MCP.
docker.io/psyb0t/decidealot:v0.7.2 -
Arbitype
MCP serversTyped decision tools for AI agents, powered by TypeSafe Jev.
arbitype@0.7.0 -
JEV-Paper-Radar
SkillsTurn research interests or paper links into a ranked reading list in Claude. Retrieve public abstracts, keep reasons and sources, and export HTML/CSV/JSON/RSS. Uploadable skill; no separate model API key. CLI and scheduled Jev/Claude workflows also included.
git clone https://github.com/Eliot5566/JEV-Paper-Radar.git -
agentgrasp
MCP serversYes/no questions about local files, and relevant-file search, with TypeSafe Jev
agentgrasp@0.1.0 -
Jev MCP Server
MCP serversMCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
jev-mcp-server@0.2.2 -
judgevet
MCP serversAsk TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
judgevet@0.23.0 -
Jev MCP
MCP serversTyped decisions with Jev / System One via OpenRouter or TypeSafe: classify, verify, rerank, decide.
ghcr.io/freepik-company/jev-mcp:v0.3.1 -
jevway
MCP serversHand a browser goal to TypeSafe Jev in your Chrome or a throwaway one; get one checked summary.
jevway@0.5.3 -
JevLint-LE
MCP serversLint questions for TypeSafe's Jev and OpenAI's Luna offline, or ask the model itself with your key.
jevlint-le-mcp@0.8.1 -
AgentCompass
SkillsDeterministic multi-agent task router & subscription quota scheduler for Claude Code, Codex, Gemini CLI (Antigravity), Grok, and Paseo. Routes sub-agents by model DNA, ability floor, and 5h/7d rate-limit windows with a PreToolUse spawn gate.
git clone https://github.com/akiiwa-games/AgentCompass.git -
Politicians by Jev
MCP serversAsk anything about 100 famous US politicians; Jev, TypeSafe AI's model, scores all 100 and picks.
-
jev-seo
MCP serversFree Rust SEO and GEO toolkit powered by TypeSafe Jev: 58-rule audits, site crawls, AI citation checks, rank drift, CI gates, 15-tool MCP. Zero cost.
git clone https://github.com/AkashPriyadarshii/jev-seo.git -
jev-judge-mcp
MCP serversTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
git clone https://github.com/PyModel/jev-judge-mcp.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.