# NanoClaw NanoClaw is a lightweight, secure personal AI assistant that runs each agent in its own isolated container on your own server. It is open source and self-hosted, installable on Docker Hub and Unraid. Canonical page: https://ourlocalhost.com/app/120/nanoclaw ## Description NanoClaw is a lightweight, secure personal AI assistant that runs each agent in its own isolated container on your own server. It provisions agents (for example in Slack) so every one gets its own bot identity, container, and memory, and lets you spawn specialised teammate agents from chat. Built as a minimal, fully readable alternative to OpenClaw, it's aimed at self-hosters who want a controllable AI agent they can actually understand and customise. ## Platform availability Available on 1 of 9 platforms: Unraid. ## Health score 73/100 (Good), based on 5 of 5 factors. - Maintained: 100 (last commit 17 days ago) - Popular: 90 (30,881 GitHub stars) - Easy to install: 35 (1 install platform, install notes, Docker image) - Light to run: 30 (4 GB minimum RAM) - Security check: 70 (no serious findings, 8 minor, CI, tests) ## Links - Official website: https://nanoclaw.dev - Docker Hub: https://hub.docker.com/r/bitcryptic/nanoclaw - Unraid: https://ca.unraid.net/apps/nanoclaw-0pi1wj01gfh6vc?q=NanoClaw ## Common questions ### How do I install NanoClaw on a new server? Clone the repository and run bash nanoclaw.sh from a fresh checkout. The script installs missing Node, pnpm, and Docker, registers an Anthropic credential, builds the agent container, and pairs your first channel. If a step fails, Claude Code is invoked automatically to diagnose and resume. ### How do I migrate an existing NanoClaw v1 install to v2? Run bash migrate-v2.sh from a fresh v2 checkout next to v1, not from inside a Claude session. It merges the .env file, seeds the v2 database from registered groups, copies group folders, session data, scheduled tasks, selected channel adapters, and channel auth state, then builds the container. It does not flip the service, so switch to v2 only after testing. ### Why does the agent ignore some of my messages? Messages must start with the configured trigger word, such as @Andy help me. If the trigger is missing or appears later in the sentence, NanoClaw ignores the message. ### What should I check if a v2 setup stops working or drops messages? Check for host startup stops, container spawn errors, dropped messages, silent agents, and stuck sessions. ## Alternatives - Alpaca - Ollama Client: Alpaca is an Ollama client where you can manage and chat with multiple models, Alpaca provides an easy and begginer friendly way of interac… - AnythingLLM: AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug… - ChatGPT: ChatGPT is a generative artificial intelligence chatbot developed by OpenAI and launched in 2022. - Claude: AI assistant for chat and API, performing summarization, search, writing, Q&A, and coding with high reliability, customizability, priva… - DeepSeek: DeepSeek is a state-of-the-art AI assistant designed to provide intelligent, conversational support across diverse tasks. - Ensu: Private offline on-device local LLM app by Ente, open source code, no accounts or tracking, and works cross-platform on mobile and desktop… - Hermes Agent: Hermes Agent is a self-improving AI agent by Nous Research that creates and refines skills from experience, builds a persistent model of yo… - Jan.ai: Open-source offline AI chat software supporting local LLMs, cloud model connections, custom assistant creation, OpenAI-compatible API, and… - Microsoft Copilot: Microsoft Copilot, formerly known as Bing Chat, is an AI chat interface used to converse with Microsoft hosted OpenAI and Claude models wit… - OpenClaw: OpenClaw is an open-source, self-hosted AI assistant gateway that connects large language models (LLMs) to Discord, Telegram, and WhatsApp,… - Poe: Poe is a web-based AI platform that hosts multiple assistant bots—including Claude and various GPT and image/audio models—to provide conver… - Secret Llama: Fully private offline chatbot runs locally in browser, with no server or installation needed. --- Source: Our Local Host (https://ourlocalhost.com/app/120/nanoclaw), the self-hosted and open-source app directory.