Highlights
- Pro
Stars
A Python framework for AI-driven character animation using neural networks.
AI-powered news aggregator with structured multilingual summaries and push notifications
AI-powered offensive security agent with 7,300+ actionable security skills. Autonomous pentesting powered by MITRE ATT&CK (2,000+ Atomic tests), CIS Benchmarks (1,500+ controls), OWASP, NIST. Lazy-β¦
Hundreds of models & providers. One command to find what runs on your hardware.
An AI skill that teaches language models how to perform intelligent security reviews of agent skills. Unlike static scanners that match patterns, this skill enables contextual threat analysis, inteβ¦
The Applicant Profile Protocol (APP) is an open, JSON-based specification for representing a job applicantβs professional profile in a structured, interoperable, and extensible manner.
Experimental: Robot Control for Strands Agents.
This is the code for the FSE26 paper: Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking, the research paper can be referred at https://arxiv.org/pdf/2512.21236
A modern postMessage tracker including additional features, inspired by Frans Rosens postmessage tracker. A port of chrome Manifest V3 "FancyTracker" to Firefox.
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
Agentic Red-Team Manager: Automated, Safe Adversarial Testing for Agentic Systems
π Token-Oriented Object Notation (TOON) β Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device because it runs 100% locally. There are no cloud uploads and no third-party β¦
π The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
SecureMCP is a security auditing tool designed to detect vulnerabilities and misconfigurations in applications using the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction)β¦
a security scanner for custom LLM applications
Prototype of Full Agentic Application Security Testing, FAAST = SAST + DAST + LLM agents
Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...)
A comprehensive reconnaissance and vulnerability scanning tool that combines multiple security assessment capabilities into a single automated workflow.
Make your GenAI Apps Safe & Secure π Test & harden your system prompt