Nanoclaw

Discover The NanoClaw

Nanoclaw is a personal Claude assistant built for simplicity and security. It's a lightweight alternative to OpenClaw - one process, a handful of files, no microservices. Features include WhatsApp integration, per-group memory, scheduled tasks, and container isolation. Built on Claude Agent SDK with AI-native setup.

NanoClaw Features

Small enough to understand

One process, a handful of source files. Small enough that you can read and understand the entire codebase.

Secure by isolation

Agents run in Linux containers. They can only see what's explicitly mounted. Bash is safe because it runs inside the container.

Built for one user

This isn't a monolithic framework. It's working software that fits your exact needs. Fork it, have Claude Code make it match yours.

AI-native

No installation wizard; Claude Code guides setup. No dashboard; ask Claude. No debugging tools; describe the problem.

Skills over features

Contributors add Claude Code skills like /add-telegram that transform your installation. You end up with clean code that does exactly what you need.

Best harness, best model

Runs on Claude Agent SDK, which means you're running Claude Code directly. The harness matters. A good one gives smart models superpowers.

NanoClaw FAQ

• How is NanoClaw different from OpenClaw?

NanoClaw takes a fundamentally different approach. Where OpenClaw is a large-scale framework with thousands of source files and dozens of dependencies, NanoClaw is a lightweight personal AI agent built around 15 source files that you can read and understand in a single sitting. NanoClaw uses OS-level container isolation (Docker or Apple Container) to sandbox every agent session, rather than relying on application-level permission checks. If you're looking for a secure, minimal alternative to OpenClaw that you can fully audit and customize, NanoClaw is designed for exactly that.

• Is NanoClaw secure?

Security is a core design principle. Every agent session runs inside an isolated Linux container with its own filesystem, IPC namespace, and process space. Agents can only access directories that are explicitly mounted, and there's no ambient access to your system. Because the entire codebase is around 3,900 lines of code across 15 files, you can realistically audit everything the software does. This combination of container-level isolation and a small, auditable codebase makes NanoClaw one of the most transparent and secure ways to run AI agents.

• What messaging apps does NanoClaw support?

NanoClaw ships with WhatsApp support out of the box and can be extended to work with Telegram, email, and other channels through the skills system. Adding Telegram is as simple as running the /add-telegram skill, which walks you through the full setup. The architecture is designed so that messaging channels are modular, so you can run one or multiple channels side by side, each with their own configuration.

• Can I run NanoClaw on Linux?

Yes. NanoClaw runs on both macOS and Linux. On Linux, Docker is used as the container runtime and is configured automatically during setup. The system requirements are Node.js 20 or later, Claude Code, and a container runtime (Docker on Linux). The /setup skill handles all dependency checks and configuration for your platform.