nanocoai/nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

What it solves

NanoClaw 是一个轻量级的 AI 助手框架，专为想要在多个消息平台上以安全、可定制且保护隐私的方式运行 AI 代理的用户设计。它通过将代理隔离在各自的 Linux 容器中，避免了运行具有广泛系统访问权限的复杂 AI 软件所带来的安全风险，确保代理只能访问明确挂载的目录。

How it works

NanoClaw 使用单一的 Node.js 主机进程作为路由器。当来自消息应用（如 Telegram 或 Discord）的消息到达时，主机将其路由到特定代理组的会话，并写入 inbound SQLite 数据库。运行 Claude Agent SDK（通过 Bun）的沙盒 Docker 容器轮询该数据库，处理请求，并将响应写入 outbound SQLite 数据库，随后主机将响应返回给用户。

Who it’s for

它面向希望拥有最小化、"AI 原生" 代码库的个人用户，他们可以轻松理解、fork 并使用 Claude Code 等 AI 工具自行定制，而不必依赖大型、单块式的框架和复杂的配置文件。

Highlights

  • Container Isolation: Agents run in Docker containers to prevent host system access.
  • Multi-channel Support: On-demand installation of adapters for WhatsApp, Telegram, Discord, Slack, and more.
  • Credential Security: API keys are managed via OneCLI's Agent Vault, so agents never hold raw keys.
  • Bespoke Customization: Designed to be modified directly in the code via AI prompts rather than through config files.
  • Scheduled Tasks: Ability to set up recurring jobs with optional script gates.
  • Flexible Model Providers: Native support for Claude, with options for OpenAI, Google, DeepSeek, and local models via Ollama.