Starred repositories
Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly.
Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
A small set of tools to process ICS files from the command line (or Mutt), create ICS files, and submit them to Owncloud's calendar (or a WebDAV)
an interfacepcb to supply and use the YAMAHA DB50 XG board stand alone
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.
OpenAnt from Knostic is an open source LLM-based vulnerability discovery product that helps defenders proactively find verified security flaws while minimizing both false positives and false negati…
To evaluate the RAGRecon system, we used two datasets: 'Conventional CTI', derived from 24 general cybersecurity reports and 'Blockchain CTI', from 28 blockchain-specific reports. Each dataset cons…
The source code for the arXiv paper titled "KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning".
A web interface to create custom vector-based visualizations on top of RAWGraphs core
Seminar on Limitations of Interpretable Machine Learning Methods
Machine Learning-based Intrusion Detection System (IDS) tailored for resource-constrained networks
A curated collection of public industrial datasets.
LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
DeepTeam is a framework to red team LLMs and LLM systems.
A list of free LLM inference resources accessible via API.
A simple example of VAEs with KANs
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Kimi K2 is the large language model series developed by Moonshot AI team
Various public documents, whitepapers and articles about APT campaigns
pretrained BERT model for cyber security text, learned CyberSecurity Knowledge