titanicprime/moltbot-safe

Reference execution layer for governed AI agent actions, with bounded synthetic destinations, runtime adapters, and retained execution evidence.

2 best points · 1 comments · 1 Hacker News post · 8 GitHub stars · View on GitHub

Hacker News discussions

• Moltbot-safe: a minimal, permissioned, sandboxed execution engine for AI agents (2 points, 1 comments, by andredelima, 2026-01-28)