Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.

PixelFerrite is a C++20 security simulation framework with a Metasploit-style console for module workflows, image-based artifact generation, and workspace-isolated runtime for authorized research and validation.

AI proposes. Humans decide. Source-available AI engineering OS/control plane for governed code change: policy gates, model routing, PR/CI evidence binding, replayable evidence bundles, chained receipts, multi-repo traceability, and human review.

OpenClaw plugin that prevents social agents from reading the main agent's workspace, config, and credentials. Fills the gap where workspaceOnly enforces writes but not reads. Eight audit versions, 6 blockers fixed.

OpenClaw plugin for durable specialist AI agents with isolated workspaces, memory, state, and /persona routing.