Home/AI Agents/nanoclaw
nanoclaw logo

nanoclaw

nanocoai/nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security, connecting to various messaging apps using Anthropic's Agents SDK

GraphCanon updated 1d · GitHub synced 1d · 29 views this month

31k stars13k forksLast push 1d TypeScript MIT

Decision brief

A lightweight alternative to OpenClaw that runs in containers for security, connecting to various messaging apps using Anthropic's Agents SDK.

Good fit when

  • When your goal is a secure environment leveraging Docker containers for running AI agents across multiple messaging platforms including WhatsApp, Telegram, Slack, Discord, and Gmail.
  • If you want diagnostics and recovery support during setup provided by Claude Code from Anthropic, directly integrated into the process to aid troubleshooting and resume operations automatically.

Avoid when

  • When working in environments that do not allow or require Docker for security reasons since Nanoclaw mandates its use to ensure isolation and safety.
  • If your project needs more extensive community support or a wider array of pre-built integrations; Nanoclaw is a lightweight alternative and might lack the breadth of capabilities offered by larger,老牌

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (0d since push)
As of 1d
Provenance
Not a fork · Organization account
As of 1d
Security (OSV)
2 low (2 low)
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install nanoclaw
npm

How it fits your stack(7)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Provides a secure environment for AI agents by running them inside containers. Supports multiple messaging platforms and leverages Claude Code from Anthropic for diagnostics and resume operations during setup.

Capability facts

CLI
CLI entrypoint

Source: package.json:bin|scripts · Aug 19, 2026

MCP server
No MCP server detected

Source: repo_scan · Aug 19, 2026

Languages
typescript, javascript

Source: github.language+package.json · Aug 19, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Aug 19, 2026)

- Node.js 20+ and pnpm 10+ (the installer will install both if missing)
Source link

Tags

README

Quick Start

git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
cd nanoclaw-v2
bash nanoclaw.sh

nanoclaw.sh walks you from a fresh machine to a named agent you can message. It installs Node, pnpm, and Docker if missing, registers your Anthropic credential with OneCLI, builds the agent container, and pairs your first channel (iMessage, Telegram, Discord, WhatsApp, or a local CLI). If a step fails, Claude Code is invoked automatically to diagnose and resume from where it broke.

Migrating from NanoClaw v1?

Run from a fresh v2 checkout next to your v1 install:

git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
cd nanoclaw-v2
bash migrate-v2.sh

migrate-v2.sh finds your v1 install (sibling directory, or NANOCLAW_V1_PATH=/path/to/nanoclaw), migrates state into the v2 checkout, then execs into Claude Code to finish the parts that need judgment (owner seeding, shared-memory migration, fork-customisation replay).

Run the script directly, not from inside a Claude session — the deterministic side needs interactive prompts and real shell I/O for Node/pnpm bootstrap, Docker, OneCLI, and the container build.

What it does: merges .env, seeds the v2 DB from registered_groups, copies group folders + session data + scheduled tasks, installs the channel adapters you select, copies channel auth state (including the Baileys keystore for WhatsApp — LID mapping is now resolved per-message by the Baileys v7 adapter, not migrated), builds the agent container.

What it doesn't: flip the system service. Pick "switch to v2" at the prompt, or do it manually after testing — your v1 install is left untouched.

See docs/v1-to-v2-changes.md for what's different and docs/migration-dev.md for development notes.


Requirements

  • macOS or Linux (Windows via WSL2)
  • Node.js 20+ and pnpm 10+ (the installer will install both if missing)
  • Docker Desktop (macOS/Windows) or Docker Engine (Linux)
  • Claude Code for /customize, /debug, error recovery during setup, and all /add-<channel> skills

License

MIT

Badge image

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.