Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Repository Index
47,133 repositories indexed
1–24 of 28 · Most stars
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
- agent-security
- agent-skills
- agentic-ai
- ai-security
A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, slack, MS), Email sending, Background jobs, Landing page, Payments (Stripe, Polar.sh), Shadcn UI, S3 file upload. AI-ready with tailored AGENTS.md, skills, and Claude Code plugin. One cmd deploy. Powered by Wasp full-stack framework.
- full-stack
- open-source
- saas
- nodejs
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
- claude-code
- geoguessr
- geolocation
- osint
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.
- adversarial-ai
- claude-code
- cursor
- electron-security
TranslatedBased on an in-depth REA teardown, a high-fidelity recreation of the official Claude desktop UI. Recreates 30 independent React components and 8 hardcore interaction physics algorithms, and comes with a 3000+ line reverse-engineering analysis manual.
- anthropic
- audioworklet
- claude
- design-system
Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
- ai-safety
- ai-security
- claude-code
- llm-agent
Cross-platform desktop LLM client for OpenAI ChatGPT, DeepSeek R1, Anthropic Claude and more, with a focus on privacy and security.
Cover your Mac's screen with a hotkey while AI agents keep running, even with the lid closed. The covered screen glows when Claude Code, Codex or Gemini needs you. Touch ID unlock.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Audit and fix your Mac's security in one command. No agent, no signup, open source.
- cli
- compliance
- endpoint-security
- golang
CLI tool for running coding agents inside hardware-isolated microVMs
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.
Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.
- ai
- claude-code
- codex
- devcontainer
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
- autoresearch
- claude-code
- cli
- developer-tools
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.
One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git
It falls out of your notch. Hotkey, repo, Return: your terminal opens with Claude Code, Codex or any agent already running. Free, MIT, local-only macOS.
Keep your secrets out of your AI coding agents. A local HTTPS proxy that swaps real credentials with placeholders and injects them at the network boundary.
AI writes. SPARDA proves. A deterministic, offline gate that catches when an AI edit removes a guard, exposes a route, or breaks an invariant — no API key, right in the agent edit loop.
- ai-agents
- ai-code-review
- authorization
- bola