16 packages found
A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
Canonical unified MCP server in golang for Hugo sites — oauth register and self registered token
Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP
AI text humanizer for prose, code & academic writing. 100+ patterns, two-pass audit, three-tier scoring, voice injection
The enforcement tool for Canonical-Driven Development (CDD). Audit, generate, and guard your project documentation. Zero
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
Teaches Claude to use a dozen visualization-building tools — raster, SVG, web, video, terminal, interactive, gaze plots,
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MC
Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 17 security hardening layers
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.