- Rochester, NY
- http://jasonross.info
- @rossja
- @algorythm@infosec.exchange
Stars
A visual-based graph node editor for training computer vision models.
Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot
AI Code Security Anti-Patterns distilled from 150+ sources to help LLMs generate safer code.
Open-source AI hackers to find and fix your app’s vulnerabilities.
AI agent for autonomous cyber operations
Development platform to debug, chat, inspect, and evaluate MCP servers, MCP apps, and ChatGPT apps.
Real-time webcam demo with SmolVLM and llama.cpp server
A practical approach to managing multiple AI agents in Cursor through strict file-tree partitioning and domain boundaries.
A low-cost approach to testing AI chat experiences and security concepts
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
21 Lessons, Get Started Building with Generative AI
Python SDK for creating, managing and running agents with Agentforce
Official inference framework for 1-bit LLMs
A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more.
Security scanner for AI agents, MCP servers and agent skills.
MCP Toolbox for Databases is an open source MCP server for databases.
Meet Ava, the WhatsApp Agent
Minimal and educational implementation of an LLM agent.
Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.
Curated list of Open Source project focused on LLM security
Vibe Coding? Cool story. But your vibe might be "security breach waiting to happen." Introducing VibePenTester, the AI pen-tester who rolls its eyes at your half-baked code, discovers your vulnerab…
Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP".