
Project-Onyx
Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion…

Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion…

AI governance and evidence gateway for multi-provider LLM applications. FastAPI + optional Rust core for policy, WAF, egress, rate limits, sessions,…

An open-source framework for verifiably private AI inference

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

Ed25519 signed receipts + Cedar policies for AI agents. Finance mandate gate (Legate), proof packs, 3 IETF Internet-Drafts. npx protect-mcp

Cryptographically signed, replay-verifiable evidence layer for AI agents. Governs actions in the loop, produces Ed25519-signed receipts linked into a…

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

OWASP Web Security Testing Guide RAG system with ChromaDB, MCP for Claude Code

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

🦫 | GoRedOps is a repository dedicated to gathering and sharing advanced techniques and offensive malware for Red Team, with a specific focus on…

reverse engineering SynthID for text


Encrypted command‑and‑control (C2) research framework for cybersecurity education, red team labs, and secure client‑server communication experiments.

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP

Research runtime for differentiable neural computers, GPU-based CPU emulation, and program synthesis. Features neural ALU, constant-time crypto, JEPA…

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

Public version of the Entropica repo

Implementation of optimal coupling-based distortion-free text watermarking to embed detectable signals in LLM-generated text while preserving quality.