Deterministic execution boundary for AI systems enforcing signed approvals, replay protection, and cryptographic receipts.
-
Updated
Feb 17, 2026 - Python
Deterministic execution boundary for AI systems enforcing signed approvals, replay protection, and cryptographic receipts.
Secure Agent Operating Environment — SATL envelopes + ToolGate + red-team hardened MVP (v0.1.0 RT-Hardened)
Inspired from https://github.com/anthropic-experimental/sandbox-runtime. A python sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Add a description, image, and links to the secure-agents topic page so that developers can more easily learn about it.
To associate your repository with the secure-agents topic, visit your repo's landing page and select "manage topics."