InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. prismor

    Agents & frameworks

    Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

    Indexed GitHub, PrismorSec 487 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/PrismorSec/prismor.git
  2. dsh-auto-review

    Agents & frameworks

    Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

    Stale GitHub, PerryLink 247 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/PerryLink/dsh-auto-review.git
  3. Asrs Reports

    MCP servers

    NASA Aviation Safety Reporting System (ASRS) — de-identified aviation safety incident narratives.

    Stale Official MCP Registry, io.github.pipeworx-io Updated 17 days ago 3 notes

    @pipeworx/mcp-asrs-reports@0.2.1
  4. Full toolkit (100+ tools). Payment-safety 6-tool MCP: /mcp/payment-safety

    Stale Official MCP Registry, dev.moneytools Updated 4 days ago 1 note

  5. Correct Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.

    Stale GitHub, MohammedAtya 7 ★MITUpdated 32 days ago

    git clone https://github.com/MohammedAtya/guardrail-forge.git
  6. promptguard

    Prompts

    Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

    Stale GitHub, mturac 76 ★MITUpdated 3 months ago

    git clone https://github.com/mturac/promptguard.git
  7. langkit

    Prompts

    🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀

    Stale GitHub, whylabs 1,000 ★Apache-2.0Updated 24 months ago

    git clone https://github.com/whylabs/langkit.git
  8. arifOS

    MCP servers

    Independent policy kernel for AI agents: judge before execute. F1–F13 floors, VAULT999 receipts. Not a model. Not a chatbot.

    Indexed GitHub, ariffazil 53 ★AGPL-3.0Updated today

    git clone https://github.com/ariffazil/arifOS.git
  9. agent-passport-system

    MCP servers

    Open protocol and TypeScript SDK for AI agent authority: identity, scoped delegation, enforcement before the action, and signed receipts.

    Indexed GitHub, agent-passport-system 67 ★Apache-2.0Updated today

    git clone https://github.com/agent-passport-system/agent-passport-system.git
  10. armguard-mcp

    MCP servers

    Safety-first MCP server for ROS 2 robot arms: server-side safety envelope, human approval, audit

    Stale Official MCP Registry, io.github.Lynn-hh Updated 22 days ago 1 note

    armguard-mcp@0.1.1
  11. node9-proxy

    Agents & frameworks

    Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.

    Indexed GitHub, node9-ai 225 ★Apache-2.0Updated yesterday

    git clone https://github.com/node9-ai/node9-proxy.git
  12. Mhra Alerts

    MCP servers

    MHRA drug and device safety alerts, recalls and Drug Safety Update bulletins, sourced from the…

    Stale Official MCP Registry, io.github.pipeworx-io Updated 13 days ago 3 notes

    @pipeworx/mcp-mhra-alerts@0.2.1
  13. AwesomeResponsibleAI

    Docs & tutorials

    A curated list of awesome academic research, books, code of ethics, courses, databases, data sets, frameworks, institutes, maturity models, newsletters, principles, podcasts, regulations, reports, responsible scale policies, tools and standards related to Responsible, Trustworthy, and Human-Centered AI.

    Stale GitHub, AthenaCore 157 ★MITUpdated 12 days ago

    git clone https://github.com/AthenaCore/AwesomeResponsibleAI.git
  14. An open database of real-world AI agent incidents.

    Stale GitHub, Continuum-AI-Corp 30 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git
  15. 5,660 AI security links: prompt injection, LLM & AI agent security, MCP, coding agents, agent skills & supply chain, red teaming, guardrails, sandboxing, incidents & CVEs, governance. 570 arXiv papers, 1,155 GitHub repos, 570 X posts, 29 categories of plain markdown you can grep, diff and fork. Obsidian vault export. Added, not endorsed.

    Stale GitHub, AnthonyHerman 8 ★CC-BY-4.0Updated 5 days ago

    git clone https://github.com/AnthonyHerman/ai-security-corpus.git
  16. ThumbGate

    MCP servers

    ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

    Indexed GitHub, IgorGanapolsky 31 ★MITUpdated yesterday

    git clone https://github.com/IgorGanapolsky/ThumbGate.git
  17. lintlang

    Prompts

    Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

    Stale GitHub, hermes-labs-ai 147 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/hermes-labs-ai/lintlang.git
  18. gargantua

    MCP servers

    Native macOS system cleaner with YAML-driven safety rules, local AI explainability via MLX, and an MCP server for agent-controlled cleanup workflows.

    Indexed GitHub, inceptyon-labs 79 ★AGPL-3.0Updated yesterday

    git clone https://github.com/inceptyon-labs/gargantua.git
  19. swing-skills

    Skills

    Open-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add

    Stale GitHub, TheStack-ai 41 ★MITUpdated 6 months ago

    git clone https://github.com/TheStack-ai/swing-skills.git
  20. autorun

    Skills

    Claude Code & codex plugin + Gemini cli extension to keep ai running, keep data safe, plan better, and keep running until tasks are done.

    Indexed GitHub, ahundt 13 ★Custom licence (see repository)Updated today

    git clone https://github.com/ahundt/autorun.git
  21. AgentLoom

    Agents & frameworks

    Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

    Indexed GitHub, linora-u 169 ★Updated 3 days ago

    git clone https://github.com/linora-u/AgentLoom.git
  22. phantom-secrets

    MCP servers

    Stop AI coding agents from leaking your API keys. Local proxy + MCP that swaps real secrets for phm_ tokens — works with Claude Code, Cursor, Windsurf, and Codex.

    Indexed GitHub, ashlrai 20 ★MITUpdated today

    git clone https://github.com/ashlrai/phantom-secrets.git
  23. ntm

    Agents & frameworks

    Named Tmux Manager: a Go control plane to spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Antigravity, omp, Grok) across tmux panes - graph-aware work triage, safety policy and approvals, Agent Mail coordination, checkpoints/timelines, and robot JSON + REST/SSE/WebSocket/OpenAPI surfaces.

    Indexed GitHub, Dicklesworthstone 464 ★Custom licence (see repository)Updated today

    git clone https://github.com/Dicklesworthstone/ntm.git
  24. Skills Claude Code pour créer ton SaaS personnel (Cloudflare, Convex, Lumail, Stripe) : grill-me, audit-safety et plus. Ressource : codelynx.dev/fx

    Stale GitHub, Melvynx 40 ★MITUpdated 4 days ago

    git clone https://github.com/Melvynx/ai-maxxing-skills.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.