InnerVault

Library

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

Results

  1. Public method documents. How the work is thought and governed. Self-taught, in Dunedin. Not a commercial offer.

    Indexed GitHub, Lycheetah 5 ★MITUpdated 3 days ago

    git clone https://github.com/Lycheetah/Lycheetah-Framework.git
  2. 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 8 days ago

    git clone https://github.com/hermes-labs-ai/lintlang.git
  3. 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 yesterday

    git clone https://github.com/ashlrai/phantom-secrets.git
  4. Agent Skills package for bounded coding-agent missions, and a Claude Code hook that asks before existing files change. Pre-registered study: the hook cut cleanup harm from 0.196 to 0 over 224 runs; the skill text alone did not.

    Stale GitHub, vladimirrott 6 ★MITUpdated 12 days ago

    git clone https://github.com/vladimirrott/patton-protocol.git
  5. Catch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-of-proof judge, framework-agnostic.

    Indexed GitHub, tonydzi 6 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/verbatim-citation-gate.git
  6. creedspace-mcp-server

    MCP servers

    Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.

    Stale Official MCP Registry, io.github.Creed-Space Updated 3 months ago 1 note

    @creedspace/mcp-server@1.1.4
  7. humane-proxy

    MCP servers

    AI safety middleware — detects self-harm and criminal intent in LLM prompts.

    Stale Official MCP Registry, io.github.Vishisht16 Updated 4 months ago 2 notes

    humane-proxy@0.6.0
  8. agent-leash

    Skills

    LEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.

    Indexed GitHub, tonydzi 5 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/agent-leash.git
  9. Scramble statistical AI text watermarks by rewriting with a local model (vLLM, Ollama), and strip C2PA, EXIF, XMP and invisible Unicode. Agent skill plus Python CLI.

    Stale GitHub, novatechflow 7 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/novatechflow/ai-watermark-scrambler.git
  10. postgres-scout-mcp

    MCP servers

    Scout your PostgreSQL databases with AI - safety features, monitoring, and data quality

    Stale Official MCP Registry, io.github.bluwork Updated 8 months ago 1 note

    postgres-scout-mcp@1.0.3
  11. mongo-scout-mcp

    MCP servers

    Scout your MongoDB databases with AI - safety features, live monitoring, and data quality

    Stale Official MCP Registry, io.github.bluwork Updated 8 months ago 1 note

    mongo-scout-mcp@1.0.3
  12. agentguard

    MCP servers

    AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.

    Stale Official MCP Registry, io.tooloracle Updated 6 months ago 1 note

  13. healthguard

    MCP servers

    HealthGuard - 12-tool health/medical AI safety MCP: PII redaction, HIPAA, GDPR Art.9.

    Stale Official MCP Registry, io.tooloracle Updated 6 months ago 1 note

  14. oasis

    Skills

    The open-source coding agent for any model: terminal and self-hosted web app, Claude Code plugins, subagents, and work that is actually verified.

    Indexed GitHub, FAHTHIZ 5 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/FAHTHIZ/oasis.git
  15. AAAA-Nexus MCP

    MCP servers

    Formally verified AI safety APIs. 75+ endpoints, pay-per-call via USDC x402, no signup.

    Stale Official MCP Registry, io.github.AAAA-Nexus Updated 6 months ago 1 note

    aaaa-nexus-mcp@0.1.1
  16. Regulated-industry AI compliance: EU AI Act, APRA, NIST AI RMF, ISO 42001, AU AI Safety.

    Stale Official MCP Registry, io.github.uchit Updated 5 months ago 1 note

    @hellouchit/mcp-regulated-ai-compliance@0.2.3
  17. little-canary

    Skills

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

    Stale GitHub, hermes-labs-ai 39 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/hermes-labs-ai/little-canary.git
  18. aizee

    Skills

    The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee

    Indexed GitHub, m3taz-ahmed 6 ★MITUpdated 2 days ago

    git clone https://github.com/m3taz-ahmed/aizee.git
  19. Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

    Stale GitHub, hermes-labs-ai 12 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/hermes-labs-ai/hermes-jailbench.git
  20. AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.

    Stale Official MCP Registry, com.fronesislabs Updated 3 months ago 1 note

  21. 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 6 days ago

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