InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. debate

    Datasets & benchmarks

    Adversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.

    Stale GitHub, lechmazur 38 ★Updated 21 days ago

    git clone https://github.com/lechmazur/debate.git
  2. AI-native SDLC skills for Claude Code: requirement intake & audit, adversarial review gate, AI test orchestration, decision re-check, release config audit

    Stale GitHub, TsCarpe 66 ★MITUpdated 11 days ago

    git clone https://github.com/TsCarpe/claude-sdlc-skills.git
  3. Responsible Prompting is an LLM-agnostic tool that aims at dynamically supporting users in crafting prompts that embed responsible intentions and help avoid harmful, adversarial prompts.

    Stale GitHub, IBM 50 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/IBM/responsible-prompting-api.git
  4. ai-berkshire

    AI repositories

    AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

    Indexed GitHub, xbtlin 17.1k ★MITUpdated today

    git clone https://github.com/xbtlin/ai-berkshire.git
  5. 22 production-quality Claude Code Skills for cybersecurity professionals , covering offensive security, defensive operations, reverse engineering, threat hunting, threat intelligence, purple team / adversary emulation, CSOC automation, AI/LLM security, mobile, OT/ICS, GRC, software supply chain security, and more.

    Stale GitHub, Masriyan 491 ★Custom licence (see repository)Updated 27 days ago

    git clone https://github.com/Masriyan/Claude-Code-CyberSecurity-Skill.git
  6. DialectOS

    MCP servers

    Spanish dialect localization MCP server: 25 regional variants, glossary, adversarial QA gates.

    Stale Official MCP Registry, io.github.KyaniteLabs Updated 35 days ago

  7. AgentTrust

    MCP servers

    Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

    Stale Official MCP Registry, io.github.vitaliiserbynassisterr Updated 8 months ago 2 notes

    mcp-agenttrust@0.1.1
  8. Eclipse Redteam MCP

    MCP servers

    Adversarial simulation for AI agents — sandboxed twins only.

    Stale Official MCP Registry, io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC Updated 21 days ago

  9. ClaudeCode-Workflow-Lab

    Agents & frameworks

    Complete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops

    Indexed GitHub, Frisher1 116 ★Updated today

    git clone https://github.com/Frisher1/ClaudeCode-Workflow-Lab.git
  10. Fable Mode

    MCP servers

    Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.

    Stale Official MCP Registry, io.github.REX-codebase Updated 2 months ago 1 note

    fable-engine@1.3.5
  11. AgentTrust

    MCP servers

    Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

    Stale Official MCP Registry, io.github.assister-xyz Updated 8 months ago 2 notes

    mcp-agenttrust@0.1.2
  12. agent-conductor

    MCP servers

    AGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.

    Stale Official MCP Registry, io.github.icohangar-ops Updated 2 months ago 1 note

    @cubiczan/agent-conductor@0.1.0
  13. TAR Engine

    MCP servers

    Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.

    Stale Official MCP Registry, io.github.qingxuantang Updated 5 days ago 2 notes

    tar-engine@0.4.0
  14. GAUNTLEX

    MCP servers

    Concurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.

    Stale Official MCP Registry, io.github.sanjoy1234 Updated 4 months ago 1 note

    gauntlex-ai@1.0.2
  15. Edgehound

    MCP servers

    Writes adversarial test suites for AI-built code. Your agent's test engineer.

    Stale Official MCP Registry, io.github.Energixe Updated 2 months ago 1 note

  16. mitre-attack-mcp

    MCP servers

    Search the MITRE ATT&CK enterprise knowledge base for adversary techniques and tactics.

    Stale Official MCP Registry, io.github.mrfentmen Updated 56 days ago 1 note

    @mrfentmen/mitre-attack-mcp@1.0.0
  17. mitre-atlas-mcp

    MCP servers

    MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 2 months ago 1 note

    mitre-atlas-mcp@1.0.9
  18. irrational

    MCP servers

    Adversarial behavioural-bias engine: audits your decisions for cognitive biases via your own AI.

    Indexed Official MCP Registry, io.github.urbanmorph Updated yesterday 2 notes

    irrational@0.1.0
  19. quorum-alpha-dash

    Agents & frameworks

    Advanced Multi-Agent AI Crude Oil Trading System with Adversarial Validation 2026

    Stale GitHub, zargarkhan1 120 ★Updated 12 days ago

    git clone https://github.com/zargarkhan1/quorum-alpha-dash.git
  20. Second Opinion

    MCP servers

    Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.

    Stale Official MCP Registry, com.secondopinionx402 Updated 42 days ago 2 notes

  21. vibe-gate-mcp

    MCP servers

    Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock

    Stale Official MCP Registry, io.github.mustafacagri Updated 40 days ago 2 notes

    vibe-gate-mcp@0.1.12
  22. Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.

    Stale GitHub, WenyuChiou 31 ★MITUpdated 17 days ago

    git clone https://github.com/WenyuChiou/agent-collab-skills.git
  23. SentEdge Idea Machine

    MCP servers

    Buy adversarially-debated AI product ideas over x402: $0.10 pulls, $1 buyouts, USDC on Base.

    Stale Official MCP Registry, ai.sentedge Updated 4 months ago 1 note

  24. Query and retrieve information about various adversarial tactics and techniques used in cyber atta…

    Stale Official MCP Registry, ai.smithery Updated 13 months ago 1 note

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.