← Back to LLM Wiki
LLM Wiki · Agent Runtime · Claw Ecosystem

NanoClaw

The containerized, security-first runtime in the Claw ecosystem. Built on Anthropic's Agent SDK with an isolated container for every tool execution.
NanoClaw exists for the workloads where the blast radius of a compromised tool call matters more than latency. Every shell command, script invocation, and tool execution runs in a fresh, short-lived container with restricted network, filesystem, and capability surface. The agent loop itself runs on Anthropic's Agent SDK — Claude-native tool use, with the sandbox layer wrapping it.
Agent Runtime Python Agent SDK Containerized Security-first

Quick Facts

Category
Agent runtime (not a model)
Language
Python
Agent loop
Anthropic Claude Agent SDK
Sandbox
Per-tool-call container (Docker / Firecracker)
Channels
Slack · Discord · WhatsApp · Gmail
Security layer
FrawdBot inline + container capability restrictions
Target hardware
Linux VPS, on-prem Linux, Kubernetes
License
Open source (see Claw ecosystem on GitHub)

Summary

NanoClaw is the security-forward member of the Claw family. Where OpenClaw optimizes for breadth of integrations and operator experience on Mac hardware, NanoClaw optimizes for isolation — a defensive posture suited to multi-tenant deployments, untrusted input (public channels, customer chat), and regulated environments where a misbehaving tool call must not be able to touch anything it shouldn't.

Every tool execution is a fresh container. The container ships with the minimal rootfs the tool needs, network egress allow-listed to the specific endpoints the tool should reach, and the filesystem scoped to a per-call workspace that's destroyed after the tool returns. Inference happens outside the sandbox; the sandbox only contains the tool-call side effects.

Architecture

When to Choose NanoClaw

NanoClaw is the right choice when any of the following dominate: multi-tenant deployment where one tenant's agent must not affect another's; user-facing chat surfaces where untrusted prompts reach tool calls; regulated environments where sandbox proofs are a compliance requirement; or workloads where the set of tools includes shell / code-execution / file-writing capabilities.

Tradeoffs vs. OpenClaw

Related

References

  1. Organized AI on GitHub
  2. The Agent Infrastructure Stack — Organized AI
  3. The Infrastructure Playbook — Organized AI