75 packages found
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
@Manavarya09Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for
Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools,
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
ASO audit MCP server for Agent Signal Optimization readiness scanning
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP ke
Audit your Claude CLI history. Visualize, browse, edit -- all with one command, all local, no auth
Deterministic refund, cancel, trial, and return policy decisions for support teams. One verdict for humans and AI agents
Make every AI chart write a reviewable proposal. Draft protocol for agent-initiated FHIR writes (Proposal → Decision → C
Teaches Claude to use a dozen visualization-building tools — raster, SVG, web, video, terminal, interactive, gaze plots,
A Claude Code skill that audits AI-generated frontend and rewrites it to remove generic AI-slop design patterns (purple
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge grap
Canonical unified MCP server in golang for Hugo sites — oauth register and self registered token
A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more.
The agent-first secret vault. Coding agents store, rotate, and share secrets — AES-256-GCM encrypted, audited, autonomou
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
Claude Code skills suite for AI-driven Odoo 17/18/19 development: read ground truth from the running instance first (fie
A Claude skill that audits designs against 19 professional design rules.
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, t
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
「MCP server that audits Japanese construction estimates and returns Bitcoin-anchored, verifiable fair-price receipts.」
A secure low code deception runtime framework, leveraging AI for System Virtualization.
Supply chain risk scorer for npm and PyPI — single-maintainer CRITICAL flags before attacks happen
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic fo
Security scanner for MCP (Model Context Protocol) servers — reads the real published npm/PyPI source, not just metadata,
The complete pre-trade verdict for Solana AI agents — cabal/coordination + honeypot + serial-rug deployer in one MCP cal
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency
MCP server for Check Point Avanan (Harmony Email & Collaboration) — security event management and MSP multi-tenant opera
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 16 tools. Works with Claude, GPT-4, or local models.
MCP server for structured email access via a local shadow database. Exposes a minimal, auditable API surface — AI agents
Secrets management for AI agents via MCP • @janeesecure
Strict AI code reviewer MCP server powered by Groq
🐕 Linux security audit tool
Protect against malicious open source packages 🤖
MCP server for reading and editing Word (.docx) documents with track changes, comments, footnotes, and structural valida
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
MCP server for Vorim AI — AI agent identity, permissions, and audit trails. 17 tools for Claude, Cursor, VS Code, and an
Claude Code skill for Xcode SwiftUI workflow auditing
The definitive SEO + GEO skill for Claude. Full site audits with scored findings, AI search optimization (Google AI Over
A Claude Code skill that builds a full monthly social media calendar, researched, audited, and production-ready with co
Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario pl
AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web
Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and
Automatically scan AUR packages for malware before installing using Claude LLM
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.