InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. aisix

    Agents & frameworks

    Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.

    Stale GitHub, api7 219 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/api7/aisix.git
  2. dsh-memory

    Agents & frameworks

    白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。

    Indexed GitHub, FuRongJun-1999 693 ★MITUpdated today

    git clone https://github.com/FuRongJun-1999/dsh-memory.git
  3. Safety-first Database Guardrail & Sandboxing MCP Server for AI Coding Agents

    Stale Official MCP Registry, io.github.RitualDev-Lab Updated 9 days ago 1 note

    @ritualdev-lab/dbshield@0.2.1
  4. agentlint

    Agents & frameworks

    Local guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more

    Stale GitHub, mauhpr 125 ★MITUpdated 10 days ago

    git clone https://github.com/mauhpr/agentlint.git
  5. harness-score

    Agents & frameworks

    Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

    Indexed GitHub, paladini 621 ★MITUpdated 2 days ago

    git clone https://github.com/paladini/harness-score.git
  6. wavefront

    MCP servers

    🔥🔥🔥 Enterprise AI Harness, connect your data to AI

    Indexed GitHub, rootflo 203 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/rootflo/wavefront.git
  7. # ========================================================== # AI EMAIL SECURITY GUARDRAILS # ========================================================== # VERSION: 1.3.0 # AUTHOR: Scott Malin, CISSP # LAST UPDATED…

    Indexed prompts.chat (CC0 prompt collection), thanos0000@gmail.com CC0-1.0

  8. Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.

    Stale Official MCP Registry, com.a2awire Updated 8 days ago 1 note

  9. Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.

    Stale Official MCP Registry, io.github.stand-out-of-my-sun Updated 27 days ago 1 note

  10. Database guardrails for AI agents: check SQL against your Vericto rules before it runs.

    Stale Official MCP Registry, com.vericto Updated 15 days ago 1 note

  11. Agent safety guardrail audit, delivered per API call as an atom service on Conduit Atoms.

    Indexed Official MCP Registry, org.aimlds Updated yesterday 1 note

  12. NeuroDock Guardrail

    MCP servers

    Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.

    Stale Official MCP Registry, io.github.tlennon-ie Updated 5 months ago 1 note

    neurodock-mcp-guardrail@0.0.5
  13. teaql-agent-kit

    Agents & frameworks

    A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.

    Stale GitHub, teaql 2,818 ★MITUpdated 20 days ago

    git clone https://github.com/teaql/teaql-agent-kit.git
  14. text classification model by Phocinae

    Stale Hugging Face Hub, Phocinae 235 ♥apache-2.0Updated 32 days ago

    Phocinae/Phocinae-Largha-150M-v1
  15. Agent Guardrails

    MCP servers

    Merge gates and safety checks for AI coding agents via MCP.

    Stale Official MCP Registry, io.github.logi-cmd Updated 7 months ago 1 note

    agent-guardrails@0.3.3
  16. joey-1

    Models

    text classification model by baselabs · transformers

    Stale Hugging Face Hub, baselabs 45 ♥mitUpdated 18 days ago

    baselabs/joey-1
  17. Guardrail MCP

    MCP servers

    Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.

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

  18. awesome-jev

    Agents & frameworks

    A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

    Indexed GitHub, cobanov 597 ★CC0-1.0Updated 2 days ago

    git clone https://github.com/cobanov/awesome-jev.git
  19. GuardRails-MCP

    MCP servers

    Local prompt regression tracker with six fictional cases and evidence for human review.

    Stale Official MCP Registry, io.github.TAM-DS Updated 31 days ago 1 note

    guardrails-mcp@0.1.1
  20. agent-guardrail

    MCP servers

    Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

    Stale Official MCP Registry, io.github.rudimentall1 Updated 3 months ago 1 note

    guardrail-mcp@1.0.2
  21. jev-judge-mcp

    MCP servers

    Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

    Stale GitHub, PyModel 48 ★MITUpdated 32 days ago

    git clone https://github.com/PyModel/jev-judge-mcp.git
  22. Action-level governance for AI agents -- control what they DO, not what they SAY

    Stale Official MCP Registry, io.github.JarvisOnM4 Updated 8 months ago 1 note

    agent-guardrail@0.1.2
  23. Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.

    Stale Official MCP Registry, com.blackwalltier Updated 2 months ago 1 note

  24. Doberman-Core

    Agents & frameworks

    Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

    Indexed GitHub, DobermanCore 243 ★Apache-2.0Updated yesterday

    git clone https://github.com/DobermanCore/Doberman-Core.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.