Notifications
Clear all
NanoClaw — Container-Isolated Anthropic Agent SDK
Container Isolation Model and Gaps
How NanoClaw's container-first design enforces isolation between agent tasks — and where the model breaks down under concurrent workloads, shared volumes, or misconfigured orchestration.
Topics: 12 /
Posts: 65
Anthropic Agent SDK Security Surface
Security properties inherited from and introduced by the Anthropic Agent SDK — API authentication, tool permission grants, and what Anthropic's hosted components see versus what stays local.
Topics: 17 /
Posts: 124
Hardening NanoClaw Deployments
Practical hardening guides for NanoClaw — from minimizing the container image to tuning network policies and locking down tool permissions in production.
Topics: 13 /
Posts: 108
No topics were found here