Logo
Deploy Now

SaaS Alternative

Claude

Categories

Self-Hosted Developer Tools Automation AI Agent Messaging Container Security WhatsApp Bot

Stars

30,591

Forks

12,845

Watchers

131

Developer links

Last Updated: 08-21-2026 09:27 PM (UTC)

NanoClaw

NanoClaw delivers a radically simple alternative to OpenClaw — a single Node.js process and a handful of files that provide the same core functionality with true container-level security isolation. Agents execute inside Docker containers on Linux or Apple Containers on macOS, where even root access inside the sandbox cannot reach the host filesystem. The platform natively runs Claude Code via Anthropic's official Claude Agent SDK, with drop-in alternatives including OpenAI Codex, OpenRouter via OpenCode, Google, DeepSeek, and local open-weight models via Ollama — configurable per agent group. Multi-channel messaging connects WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend, installed on demand through skill commands. Each agent group receives its own CLAUDE.md memory file, isolated filesystem, container sandbox, and session state — a prompt injection in one group cannot exfiltrate data from another. The OneCLI Agent Vault handles credentials so agents never hold raw API keys, while approval-gated self-modification allows agents to request new packages or MCP servers that administrators must authorize. Scheduled tasks run recurring jobs inside containers with message delivery back to users. The setup script handles dependencies, authentication, and container configuration through Claude Code conversation. Deploy on any Docker-capable Linux server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

NanoClaw
NanoClaw
NanoClaw

Benefits

  • True Container-Level Security Isolation
  • Agents execute in Docker containers with filesystem isolation enforced by the operating system, not permission checks — even root inside the sandbox cannot reach host data or other groups.
  • 13+ Messaging Channels On Demand
  • WhatsApp, Telegram, Discord, Slack, Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email installed via skill commands without carrying unused adapters.
  • Per-Group Memory and Context Isolation
  • Each agent group receives its own CLAUDE.md memory file, isolated filesystem, container sandbox, and session state preventing cross-group data leakage from prompt injection attacks.
  • Skill-Based Architecture Over Features
  • Channels and providers live as reusable skill files that Claude Code applies to your fork on demand, keeping the codebase small enough to read in eight minutes.

Features

  • Claude Agent SDK Runtime
  • Natively runs Claude Code with full toolset via Anthropic's official SDK, with drop-in alternatives for Codex, OpenCode, and Ollama per agent group.
  • MCP Server Integration
  • Register any stdio or HTTP MCP server via CLI with automatic allow-pattern derivation, approval-gated self-modification, and per-group tool isolation.
  • Scheduled Task Execution
  • Recurring jobs run inside containers on configurable schedules with message delivery back to users across any connected channel.
  • OneCLI Agent Vault
  • Credentials stored in encrypted vault with automatic injection into containers at runtime, ensuring agents never hold raw API keys or OAuth tokens directly.
  • Agent Templates
  • Stamp ready-to-run agents from reusable bundles containing instructions, MCP tools, and skills without secrets via the public template library.