Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
aisix
Agents & frameworksOpen-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.
git clone https://github.com/api7/aisix.git -
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。
git clone https://github.com/FuRongJun-1999/dsh-memory.git -
Safety-first Database Guardrail & Sandboxing MCP Server for AI Coding Agents
@ritualdev-lab/dbshield@0.2.1 -
agentlint
Agents & frameworksLocal 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
git clone https://github.com/mauhpr/agentlint.git -
harness-score
Agents & frameworksYour AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.
git clone https://github.com/paladini/harness-score.git -
wavefront
MCP servers🔥🔥🔥 Enterprise AI Harness, connect your data to AI
git clone https://github.com/rootflo/wavefront.git -
AI EMAIL SECURITY GUARDRAILS
Prompts# ========================================================== # AI EMAIL SECURITY GUARDRAILS # ========================================================== # VERSION: 1.3.0 # AUTHOR: Scott Malin, CISSP # LAST UPDATED…
-
Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.
-
Diogenes Agent Guardrails & Sandbox MCP
MCP serversAutonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
-
Vericto: database guardrails for AI agents
MCP serversDatabase guardrails for AI agents: check SQL against your Vericto rules before it runs.
-
Agent safety guardrail audit — Atom
MCP serversAgent safety guardrail audit, delivered per API call as an atom service on Conduit Atoms.
-
NeuroDock Guardrail
MCP serversAdvisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.
neurodock-mcp-guardrail@0.0.5 -
teaql-agent-kit
Agents & frameworksA model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.
git clone https://github.com/teaql/teaql-agent-kit.git -
Phocinae-Largha-150M-v1
Modelstext classification model by Phocinae
Phocinae/Phocinae-Largha-150M-v1 -
Agent Guardrails
MCP serversMerge gates and safety checks for AI coding agents via MCP.
agent-guardrails@0.3.3 -
joey-1
Modelstext classification model by baselabs · transformers
baselabs/joey-1 -
Guardrail MCP
MCP serversDeterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
-
awesome-jev
Agents & frameworksA curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
git clone https://github.com/cobanov/awesome-jev.git -
GuardRails-MCP
MCP serversLocal prompt regression tracker with six fictional cases and evidence for human review.
guardrails-mcp@0.1.1 -
agent-guardrail
MCP serversDeterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
guardrail-mcp@1.0.2 -
jev-judge-mcp
MCP serversTyped 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.
git clone https://github.com/PyModel/jev-judge-mcp.git -
Agent Guardrail MCP Server
MCP serversAction-level governance for AI agents -- control what they DO, not what they SAY
agent-guardrail@0.1.2 -
blackwall-x402-guardrail
MCP serversKeyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.
-
Doberman-Core
Agents & frameworksYour AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
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.