224 packages found
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
@zouchenzhenCodex / Claude Skill for editable thesis-defense PPTX from PDF or LaTeX while preserving a PowerPoint template. 从论文 PDF
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3F
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
A secure, containerized Model Context Protocol (MCP) server that integrates SpamAssassin for defensive email security an
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
Free startup IP protection MCP for Cursor and Claude — know what's protectable before competitors copy it
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistak
Lasso security integrations for Claude Code, including prompt-injection defenses
Passive recon tool. Zero credentials required. Finds Microsoft 365 & Google Workspace tenants, scores email security, fi
Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline wo
Self-installing personal AI orchestrator. Hand the latest blueprint file to a Claude Code session and it builds a full m
⚡ Cut LLM inference costs 80% with Programmatic Tool Calling. Instead of N tool call round-trips, generate JavaScript to
CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assista
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats aut
Fetch URLs and return clean, LLM-ready markdown with metadata and layered prompt injection defense. Configurable timeout
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides,
Markdown-first Notion MCP server. 42 tools, ~6–7× fewer response tokens vs the official Notion MCP, full round-trip fide
MCP server for TouchDesigner — build, wire, and debug networks with AI. Plus git-diffable externalization.
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
Silicon Pantheon - Tactics game played by AI agents coached by human
Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secr
Transparent and Efficient Financial Analysis
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real bro
The first multi-source MCP server for Philippine civic data: earthquakes, weather, typhoons, procurement, population, po
Save thousands of lines of code by building universal, domain-agnostic Multi-Agent Systems (MAS) through high-level sema
@erezweinstein5A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, tes
From company name to investment decision. Sieve scores startups across 7 dimensions so you know who's worth a meeting.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
MCP Server that connects Claude AI to Gmail & Google Drive for intelligent email management, file organization, and prod
Field guide to token optimization in LLM-powered applications. Compiled from Claude Code, Cline, Codex, and OpenCode.
My personal Claude Code and OpenAI Codex setup with battle-tested skills, plugins, hooks and agents that I use daily.
DOI → PDF resolver with 7-source fallback (Unpaywall, S2, arXiv, PMC, bioRxiv, publisher, Sci-Hub). Multi-agent, zero-de
A repo lists papers related to LLM based agent
Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — c
Monitor the Model Context Protocol (MCP) Registry for new, updated, and removed servers. Get real-time notifications via
AI powered automation toolkit which acts as an agent that discovers MCP servers for you. Point it at GitHub/npm/configur
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.
Cybersecurity expert skills for Claude Code — web hacking, pentest recon, secure code review, and CTF solver
(S)AGE - (Sovereign) Agent Governed Experience
Convert GitHub repositories to MCP servers automatically. Extract tools from OpenAPI, GraphQL & REST APIs for Claude Des
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
The pretty much "official" DSPy framework for Typescript