
halo-record
Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…

Security patches for unpatched llama.cpp vulnerabilities (CVE-2026-43626 through CVE-2026-43632) — Cyera Research

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

This opensource project dedicated to implementing Enterprise level AI-SPM. By doing so organizations can proactively protect their AI systems from…

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets…