153 packages found
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
An MCP server that lets AI agents operate a multi-cluster Kubernetes fleet through an Open Cluster Management hub, with
AI text humanizer for prose, code & academic writing. 100+ patterns, two-pass audit, three-tier scoring, voice injection
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
AI builds faster than anyone, with no skin in the game and no memory of yesterday. How do you govern that? With X2, deci
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude
Anti-slop content audit skill for X, ViewFT, LinkedIn, and long-form posts.
Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools,
Open-source AI research assistant for VS Code + GitHub Copilot. Connects to PubMed, OpenAlex, Semantic Scholar, Europe P
Local guardrails for AI coding agents. Wraps any MCP server and blocks destructive tool calls — DROP TABLE, rm -rf, forc
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
AI antivirus for developer agents: protect Codex, Claude Code, Cursor, Gemini, OpenCode, plugins, skills, MCP servers, a
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability
Open-source MCP runtime for governed Postgres/MySQL access: semantic capabilities, evidence-backed proposals, approval o
Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and aud
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate
Auditable UniProt MCP server with per-response SHA-256 provenance, release pinning, verification, and offline replay.
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integratin
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-deman
Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and
Make every AI chart write a reviewable proposal. Draft protocol for agent-initiated FHIR writes (Proposal → Decision → C
Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CL
MCP server for GIA Governance — runtime governance for AI agents. 33+ tools. Free starter key → gia.aceadvising.com/get-
Claude Code skills suite for AI-driven Odoo 17/18/19 development: read ground truth from the running instance first (fie
Curated marketplace of AI skills, agents, and rules for cloud, zero-trust, and compliance-aware engineering - works with
Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shad
Model Context Protocol (MCP) server for ISO27001: A stateful Model Context Protocol (MCP) server that gives Claude a com
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Context Minifier & State Guard — Local-first MCP middleware proxy
A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script
Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injec
MCP server that sits between AI agents and real systems. Evaluates every tool call before execution. Holds risky ones fo
Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals ba
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
The agent-first secret vault. Coding agents store, rotate, and share secrets — AES-256-GCM encrypted, audited, autonomou
Flutter APK/AAB security SKILL.md for OpenClaw, Codex, Claude Code, and other AI coding agents
🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️
Scan a repo for hidden prompt-injection before your AI agent trusts it — CLI, MCP server & GitHub Action. Run: npx malsk
Let agents control many desktop software directly from the cli, with one pip install, and no MCP servers.
Pre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.