Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
grasp
MCP serversReview what your coding agent did, decision by decision, with real before/after behavior.
https://github.com/arsaljamal/grasp/releases/download/v0.1.1/grasp-0.1.1.mcpb -
pi-ask-user
Agents & frameworksInteractive decision-gating extension for pi — lets AI agents ask users questions with multiple-choice and freeform answers
git clone https://github.com/edlsh/pi-ask-user.git -
ux3-product-design-harness
SkillsAgentic Design Process with Designer-in-the-Loop product judgment across User, Evidence, and Business flows.
git clone https://github.com/cis2042/ux3-product-design-harness.git -
optim-jev
SkillsJev based decision tools for claude code and codex
git clone https://github.com/Oqura-ai/optim-jev.git -
clef-mcp
MCP serversLocal MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline
clef-mcp@0.4.0 -
contrarian
SkillsDevil's advocate for coding agents. Stress-tests plans, architecture and decisions with a steel-man, an assumption audit and a pre-mortem, then gives severity-rated findings and a verdict. Works in Claude Code, Codex, Cursor, Gemini CLI, Copilot and 12 more.
git clone https://github.com/aaddrick/contrarian.git -
adr-kit
SkillsArchitecture decisions your AI coding agents actually follow. Ranked ADR retrieval and context injection, deterministic pre-commit and CI enforcement with file:line citations, guided authoring, a staleness guardian, and a key-free MCP server. Native for Claude Code, OpenAI Codex, GitHub Copilot CLI and OpenCode. MIT.
git clone https://github.com/rvdbreemen/adr-kit.git -
catalog
MCP serversSearch avva for an expert's Decision Model, then connect it: judgment from real past decisions.
-
CommitLore
MCP serversGit-native decision memory for coding agents: only the decisions still in force for the edited path
-
paypilot-ach-returns-mcp
MCP serversRead-only decision table over ACH return codes: 17 codes, 5 decisions, rule shown.
paypilot-ach-returns-mcp@0.1.1 -
WhyKit
MCP serversRead-only decisions and evidence from a Git vault, and which decisions a code change touches.
whykit@0.5.1 -
FlowState Hosted
MCP serversHosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.
-
Hunter-Seeker
MCP serversThe decision layer for AI agents: act, escalate or refuse, and every decision comes back signed.
-
Jev-Style
MCP serversLocal 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
jev-style@0.6.3 -
clawock
SkillsStock investment and portfolio decision workflows for AI agents: Claude Code, Codex, OpenClaw, DeepSeek Harness (dsh plugin) or your own script. Agents argue bull vs bear on HK and US stocks; Python reconciles the book, gates risk and scores each trading call against market prices. Pluggable quant strategies, live real-money track record.
git clone https://github.com/KCNyu/clawock.git -
neurolink
AI repositoriesThe pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide (via TypeSafe Jev). MCP-native, voice (TTS/STT/realtime), RAG, memory, file processors. Powers Tara, Yama and Clairvoyance at Juspay.
git clone https://github.com/juspay/neurolink.git -
agent-jev
Agents & frameworksAgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
git clone https://github.com/malevrigns/agent-jev.git -
AiSOC
MCP serversOpen-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
git clone https://github.com/beenuar/AiSOC.git -
Meldwork
Agents & frameworksLocal-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
git clone https://github.com/Ryder-Sun/Meldwork.git -
claude-sdlc-skills
SkillsAI-native SDLC skills for Claude Code: requirement intake & audit, adversarial review gate, AI test orchestration, decision re-check, release config audit
git clone https://github.com/TsCarpe/claude-sdlc-skills.git -
design-intelligence
SkillsRYUX gives AI agents the design intelligence to understand product context, make intentional design decisions, and evaluate what they create.
git clone https://github.com/ryuxdsgn/design-intelligence.git -
forge-of-thought
SkillsForge of Thought is an AI cognitive extension: a workshop where your idea is forged into a decision you can stand behind. You and the AI elicit the idea together until it is whole, reviewers that never saw the conversation attack it, and who decided what and why is recorded. Runs in Claude Code.
git clone https://github.com/pche-broken-artist/forge-of-thought.git -
mcp-server
MCP serversCreate, manage, and test business rules directly from your AI agent via the DecisionRules platform.
-
notion-knowledge-capture
SkillsCapture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
$skill-installer <skill-name>
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.