AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Minimalistic security tool to scan for dangerous sinks (XSS, data leakage) in codebases.

Evaluate prompts, outputs, and tool calls against AI Guard security policies within n8n workflows. Protect LLM applications from prompt injection, data leakage, and policy violations in real-time.

An LLM-based context-aware AI guardrail capable of understanding conversation context for security, safety and data leakage detection.

Local-first persistent memory for Claude Code. Each user gets their own SQLite brain in ~/.celiums/memory.db. 5 hooks + 6 MCP tools + 9 Cognitive Reflexes. Zero servers, zero accounts, zero data leakage.

ZugaShield security scanning plugin for OpenClaw — 7-layer defense + ML detection against prompt injection, SSRF, data leakage, memory poisoning, and all 10 OWASP Agentic AI risks

Identify confidential and sensitive info in source code repos with signatures (IT secret definitions).

FangcunGuard AI safety plugin for OpenClaw — multi-layer content security detection, prompt injection defense, and data leakage protection.

OpenClaw Lark/Feishu channel plugin

DSH plugin for background security audits, secret leakage detection, and command safety

Zero-dependency LLM/AI security scanner. Detects prompt injection, sensitive data leakage, excessive agency, and more — mapped to OWASP Top 10 for LLM Applications (2025). Works in Node.js, browsers, and edge runtimes.

Memory leak testing for node. Javascript memory footprinting using your favorite test runner.

solve node AWS lambda EMFILE issue

Scientific writing & document integrity guard for AI-assisted research - prompt-guided argument economy with deterministic scientific, delivery, journal, and Word integrity checks.

A Rust crate for managing content projection and navigation across polyhedron-based UI structures, with WASM bindings for web integration.

Model Context Protocol (MCP) server that exposes Muovi's public /v1 API to LLM agents (Claude Desktop, Cursor, Claude Code). Read-only, stdio mode.

MedSci Skills — a medical/scientific research skill suite for AI coding agents (Claude Code, Codex, Cursor, Copilot). The npm package is a terminal-friendly installer shortcut; the canonical distribution remains the GitHub repository and the Claude Code p

Makes all modules in Node get loaded in strict mode.

MemberJunction: Predictive Studio server-side engine (feature assembly, training, inference, experiment orchestration)

Zero-dependency label-leakage detector for tabular clinical data.