🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
Sandboxed SBOM extraction from arbitrary artifacts. Outputs traceability records and CycloneDX JSON for automation, auditability, and supply chain security.
Security-focused sandboxing core running apps via Podman containers or qemu VMs, each walled off from the rest of the desktop. Compositor-agnostic and installs cleanly on any existing system.
Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as the only way out.