InnerVault

Library

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

Results

  1. hermeneutic

    Skills

    Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

    Stale GitHub, hermes-labs-ai 9 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/hermes-labs-ai/hermeneutic.git
  2. pitbridge

    MCP servers

    Local-first MCP bridge for NinjaTrader 8 behind a deterministic guardrail engine.

    Stale Official MCP Registry, com.pitbridge Updated 4 months ago 1 note

    pitbridge@0.2.2
  3. Aegis Policy

    MCP servers

    Governance firewall and safety guardrails oracle for AI swarms.

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

  4. Kinocut

    MCP servers

    Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.

    Stale Official MCP Registry, tech.kyanitelabs Updated 7 days ago 1 note

    kinocut@2.0.1
  5. superuser

    MCP servers

    Permission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit.

    Stale Official MCP Registry, io.github.fitzyracing1 Updated 4 days ago 2 notes

    superuser@0.1.1
  6. futureagi-sdk

    Prompts

    Production-grade AI evaluation, prompt management & observability SDK. Automated evaluations with sub-100ms guardrails. No human-in-the-loop required. Python + TypeScript.

    Stale GitHub, future-agi 52 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/future-agi/futureagi-sdk.git
  7. 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
  8. aidimag

    MCP servers

    Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

    Stale Official MCP Registry, io.github.AiDimag Updated 3 months ago 2 notes

    aidimag@1.0.22
  9. Oi

    MCP servers

    Access Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.

    Stale Official MCP Registry, io.github.carhaix Updated 3 months ago 1 note

  10. mandateguard

    MCP servers

    Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.

    Stale Official MCP Registry, io.github.ezequiellich44-cmd Updated 3 months ago 1 note

    https://github.com/ezequiellich44-cmd/MandateGuard/releases/download/v1.1.0/mandateguard-1.0.0.mcpb
  11. kubeleash

    MCP servers

    Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.

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

    ghcr.io/kubeleash/kubeleash:0.3.0
  12. memini

    MCP servers

    Local-first project memory and mistake-prevention guardrails for AI coding agents.

    Stale Official MCP Registry, io.github.lumayapartners Updated 3 months ago 1 note

    memini@0.4.0
  13. Anchord (AnchorID)

    MCP servers

    Read-only MCP for identity resolution and write guardrails.

    Stale Official MCP Registry, io.github.nolenation04 Updated 7 months ago 3 notes

    @anchord/mcp-server@1.1.1
  14. 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
  15. zenable

    MCP servers

    Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails

    Stale Official MCP Registry, app.zenable Updated 13 months ago 1 note

  16. 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
  17. aidimag

    MCP servers

    Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

    Stale Official MCP Registry, io.github.anup-khanal Updated 3 months ago 3 notes

    aidimag@1.0.20
  18. guard

    MCP servers

    Local-first architecture guardrails and project context for JS/TS AI coding agents.

    Stale Official MCP Registry, io.github.codapult Updated 7 days ago 1 note

    @codapult/guard@0.14.1
  19. aiglare

    MCP servers

    Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.

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

    @nugehs/aiglare@0.2.3
  20. tracelane-mcp

    MCP servers

    Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

    Stale Official MCP Registry, io.github.tracelane Updated 39 days ago 2 notes

    @tracelanedev/mcp@0.4.0
  21. agentrisk

    MCP servers

    Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

    Stale Official MCP Registry, io.github.trycoin-ai Updated 50 days ago 1 note

    agentrisk@0.1.3
  22. suprawall-mcp

    MCP servers

    SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.

    Stale Official MCP Registry, io.github.wiserautomation Updated 7 months ago 2 notes

    suprawall-mcp-plugin@0.1.0
  23. Polis Protocol

    MCP servers

    Local-first control plane for coding agents: routing, reservations, and guardrails.

    Stale Official MCP Registry, io.github.yehudalevy-collab Updated 5 months ago 1 note

    polis-protocol@2.0.1
  24. Whiskers

    MCP servers

    Governed Docker and Kubernetes operations for AI agents: scoped keys, guardrails, human approvals.

    Stale Official MCP Registry, io.github.LupusMalusDeviant Updated 22 days ago 1 note

    ghcr.io/lupusmalusdeviant/whiskers:0.15.0

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.