InnerVault

Library

87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. spec-guard

    MCP servers

    Hold your code to what your Markdown says: the rules on a path, asked before an agent writes it.

    Stale Official MCP Registry, io.github.spec-family Updated 5 days ago 1 note

    @spec-family/spec-guard@0.35.0
  2. Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.

    Stale Official MCP Registry, io.github.aiguardrail Updated 43 days ago 1 note

  3. Guard Brasil

    MCP servers

    Detecta e mascara dado pessoal brasileiro (CPF, CNPJ, RG, e-mail) antes do texto ir a uma IA. LGPD.

    Stale Official MCP Registry, io.github.enioxt Updated 35 days ago 2 notes

    @egosbr/guard-brasil-mcp@0.2.3
  4. Code Guardian

    MCP servers

    Safe to run? Will it work? Complete? An A-F grade for any repo, plus a verify loop. Never runs it.

    Stale Official MCP Registry, io.github.LuminariSoftwares Updated 6 days ago 1 note

    code-guardian-mcp@0.7.1
  5. Free signup, 2 points, one command. Base token risk checks, route simulation, x402-paid.

    Stale Official MCP Registry, trade.musefish.a2a Updated 8 days ago 1 note

  6. 41 MCP tools for EU invoice evidence, supplier checks, market data and read-only chain queries

    Stale Official MCP Registry, io.github.PatrickPi1312 Updated 7 days ago 1 note

  7. Read-only Solana SPL/Token-2022 rug-risk check: 0-100 score (higher=riskier) with reasons.

    Stale Official MCP Registry, io.github.fitness9991 Updated 14 days ago 1 note

  8. chatvia

    AI repositories

    Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.

    Stale GitHub, chatvia 112 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/chatvia/chatvia.git
  9. agent-flow

    Skills

    Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a guard on protected paths, and a tamper-evident audit log.

    Stale GitHub, Drix10 12 ★MITUpdated 7 days ago

    git clone https://github.com/Drix10/agent-flow.git
  10. antirion

    AI repositories

    🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.

    Stale GitHub, eliasbiondo 501 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/eliasbiondo/antirion.git
  11. x402 payment safety: judge a payment against your policy before signing. Read-only, never signs.

    Indexed Official MCP Registry, io.github.base-buzz Updated today 1 note

    @paystage/x402-guard@0.4.9
  12. Check a shop, checkout or payment link, paid API or token before paying; prompt-injection scan.

    Stale Official MCP Registry, com.oroboros-design.angel Updated 4 days ago 2 notes

    angel-agent-guard@0.2.0
  13. Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

    Indexed OpenRouter model list, meta-llama Updated 18 months ago

    meta-llama/llama-guard-4-12b
  14. console

    MCP servers

    Open-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.

    Stale GitHub, Cognipeer 27 ★AGPL-3.0Updated 6 days ago

    git clone https://github.com/Cognipeer/console.git
  15. Detect and redact PII and secrets (API keys, tokens) in text, HTML or PDF before it reaches an LLM.

    Stale Official MCP Registry, io.github.fairquery Updated 31 days ago 1 note

  16. Community fork of rehan-remade/universal-modder with the built-in agent guardrail text removed. Same skills, tools and knowledge base; no guardrail layer.

    Stale GitHub, AhmedTahaAtiya 20 ★MITUpdated 27 days ago

    git clone https://github.com/AhmedTahaAtiya/universal-modder-unrestricted.git
  17. agent-guard

    Skills

    Scan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.

    Indexed GitHub, elliottwaves-20 5 ★MITUpdated 3 days ago

    git clone https://github.com/elliottwaves-20/agent-guard.git
  18. LightAgent

    Agents & frameworks

    LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

    Indexed GitHub, wanxingai 1,249 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/wanxingai/LightAgent.git
  19. Pre-purchase check for any shop, checkout or payment link, paid API or x402 endpoint.

    Stale Official MCP Registry, com.oroboros-design.angel Updated 4 days ago 1 note

  20. jevmem

    MCP servers

    Shared project rules and memory for AI coding agents: a JEVMEM.md in git, with a command guard.

    Stale Official MCP Registry, io.github.Avinash-jetwani 127 ★Updated 6 days ago 2 notes

    jevmem@0.7.8
  21. # Objective Analyze the song URL, lyrics, music video (if available), transcript, or summary provided by the user and determine whether the content is appropriate for children. Produce a factual, structured…

    Indexed prompts.chat (CC0 prompt collection), senoldak CC0-1.0

  22. scholar-loop

    Agents & frameworks

    An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

    Indexed GitHub, r2m-ai 476 ★MITUpdated 2 days ago

    git clone https://github.com/r2m-ai/scholar-loop.git
  23. Guardrails for AI coding agents — Claude Code, Codex and Antigravity — enforced by a real git pre-commit gate. One command installs AGENTS.md, path-scoped rules, skills, subagents, hooks and 13 stack presets. Plain files, offline-ready. English / 한국어

    Stale GitHub, LeeYudok 39 ★MITUpdated 6 days ago

    git clone https://github.com/LeeYudok/agents-scaffold.git
  24. plano

    AI repositories

    Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

    Stale GitHub, katanemo 7,099 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/katanemo/plano.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.