61 packages found
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microseco
MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship
Multi-driver TUI database client with a built-in MCP server. Six databases (postgres, mysql, sqlite, duckdb, clickhouse,
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats aut
Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.
Query your AWS environment with natural language.
MCP server for Caido proxy integration. Enables AI assistants like Claude Code to browse, analyse, and interact with HTT
@anthropics✓ OfficialSkills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Standalone MCP server — cross-session memory, 10-gate VERITAS build pipeline, cryptographic audit ledger, Cortex approva
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Claude Code skill for Anthropic Managed Agents — create / run / audit the cloud-hosted agent API end-to-end. 教 Claude 用
Run Claude in self-improving loops to optimize measurable goals.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CL
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 16 tools. Works with Claude, GPT-4, or local models.
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability
Implementation of the CodeAct agentic framework with Docker containers for security, MCP servers for tool integrations,
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP ke
Model Context Protocol (MCP) servers for managing homelab infrastructure through Claude Desktop. Monitor Docker/Podman c
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
An MCP server to create secure code sandbox environment for executing code within Docker containers. This MCP server pro
Turn your AI agent into a hacker by plugging in this MCP
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a s
The Atlas series — prompt skills that keep AI agents honest about the goal. atlas-contract freezes tasks into auditable
A secure, stable Rust alternative to openclaw/moltbot/clawdbot
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomou
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deplo
Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools,
Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CL
The first quantum-inspired keyring built specifically for AI coding agents. Secure secrets with superposition, entanglem
The most powerful Android RPA agent framework, next generation mobile automation.
A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD,
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit
Fast, opinionated AWS security scanner. Curated checks. Zero noise. Copy-paste fixes.
DeMCP is the first Decentralized MCP network, offering SSE proxies for MCP services and mainstream LLMs, tackling trust
A Postgres MCP server for agents — layered safety (role grant + pglast AST guard + per-tx envelope + audit log), schema
Know what your AI agent actually did. Agent Recorder logs every tool call across your MCP servers — locally, to SQLite,
A read-only Kubernetes MCP server: list resources, get resource details, retrieve pod logs, discover API resources, and
The Control Plane for MCP — secure vault, managed runtime, audit trail, and policy-based approvals.
Browse the web, directly from Cursor etc.
Wireshark-MCP，Give your AI assistant a packet analyzer. Drop a .pcap file, ask questions in plain English — get answers