Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
ElevenPowers
Skills"make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.
git clone https://github.com/SatyamSingh-Git/ElevenPowers.git -
Wavn
MCP serversThe deciding place: argue the call, decide, keep the reasons, get the work back as finished files.
-
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 -
q-claude-skills
SkillsA collection of Claude skills organized by how I think, decide, research and build.
git clone https://github.com/kju4q/q-claude-skills.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 -
ego-jev
Skillsego lite skill — each DOM step decided in ~0.4s, no LLM turn
git clone https://github.com/ZephyrDeng/ego-jev.git -
product-engineering
Skills45 agent skills from shipping three live products: decide what to build, build it with Claude Code or Codex, have a second model review it, release it.
git clone https://github.com/phuryn/product-engineering.git -
pm-copilot
MCP serversMCP server that triangulates customer support tickets and feature requests to help PMs decide what to build next
git clone https://github.com/dkships/pm-copilot.git -
turbo
SkillsA human-gated agentic software factory for Claude Code and Codex: you decide what to build and judge the result; skills shape, build, polish, ship, and learn.
git clone https://github.com/tobihagemann/turbo.git -
mcp-payway
MCP serversPayway (ex-Decidir) — Argentina card acquiring: tokenize, charge, capture, refund
@codespar/mcp-payway@0.1.0 -
BIGHUB
MCP serversDecision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
@bighub/bighub-mcp@0.2.1 -
backportcheck
MCP serversDecide whether a fix needs a backport, and to which release branches.
@reneturcios/backportcheck@0.1.0 -
iMario
MCP serversSynthetic audiences built from real people. Ask anyone anything before you decide.
-
simengine
MCP serversMonte Carlo decision-intelligence over MCP: simulate, optimize, and decide under uncertainty.
simengine-mcp@3.0.1 -
Quirna
MCP serversAsk a human before your agent acts: approval requests decided on a phone.
@quirna/mcp@0.1.2 -
agentrisk
MCP serversRisk guardrails for AI trading agents. Your agent proposes; your policy decides.
agentrisk@0.1.3 -
aiquant-lite
Agents & frameworksAI 原生 A 股投研中枢|百万级本地数据 × 量化实验 × 多模型研究 × 可追溯决策。Research deeper. Decide with evidence. · Local-first · Hermes / MCP.
git clone https://github.com/Shixi216/aiquant-lite.git -
Klarefi
MCP serversComplete regulated intake work and retrieve cited case files without deciding the case.
@klarefi/mcp@0.3.0 -
thinqOS
MCP serversMemory with judgment: decides which of your context reaches each task, per identity.
-
AgentGate
MCP serversHuman-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
@agentkitai/agentgate-mcp@0.0.3 -
security-txt-cra-lint
MCP servers13 rules that decide whether a vulnerability report ever reaches you
@readystack/security-txt-cra-lint@1.0.7 -
BuzzMeBro
MCP serversMore than one roommate on your apartment buzzer number; settings decide who rings. Canada.
-
vivac
MCP serversProvenance tree for coding agents: where you are, why, and what was already decided
vivac@0.22.1 -
nakkas
MCP serversMCP server that turns AI into an SVG artist. One rendering engine, AI decides everything.
nakkas@0.5.0
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.