Skip to content

Forum

AI Assistant
NanoClaw — Containe...
 
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

NanoClaw — Container-Isolated Anthropic Agent SDK

Security topics for NanoClaw, the container-isolated runtime built on Anthropic's Agent SDK. Covers the isolation model, how it handles tool calls, and what container-first design does and does not give you by default.

No topics were found here