Skip to main content
OpenSourceAlternatives

NanoClaw

Open source · OSI-approvedStatus: unknownNew

Self-hosted personal AI agent for WhatsApp, Telegram, and Slack

Alternative to Slack

NanoClaw is a self-hosted personal AI agent you message from the apps already on your phone. It suits individuals who want a private assistant inside WhatsApp, Telegram, Slack, or Discord without handing their life to a hosted service. This review is based on public official sources observed in October 2026, not hands-on testing. Version 2026.10.0 was current at observation with a commit one day prior, and a v1-to-v2 migration path documents an actively maintained project.[1][2][3][4][5]

Quick verdict

People who want a private assistant living inside their messaging apps will get the most from NanoClaw. Its per-session Docker containers, credential gateway, and per-agent memory keep each conversation isolated and personal. Anyone unwilling to run Docker, keep a computer on, and pay a separate AI provider should choose something else, since NanoClaw is self-hosted and brings no model of its own. If you want an assistant you can read in an afternoon and run yourself, choose NanoClaw; if you want zero setup, choose a hosted assistant instead.[1][2][3]

Key features

  • Thirteen messaging channels WhatsApp, Telegram, Discord, Slack, Microsoft Teams, iMessage, Matrix, Google Chat, Webex, Linear, GitHub, WeChat, and email via Resend connect through install-on-demand channel skills, and several can run at once.[1]

  • Per-session Docker isolation Each active session gets its own Linux container on macOS, Linux, or Windows via WSL2, so shell commands run inside the sandbox and agents see only explicitly mounted folders.[1][2]

  • Credential gateway Agents never hold raw API keys; outbound requests route through an installed gateway that injects credentials at request time and enforces per-agent policies and rate limits.[1][2]

  • Flexible isolation modes Each channel can map to its own private agent, share one agent with unified memory but separate conversations, or fold several channels into a single shared session.[1][2]

  • Per-agent workspace Every agent group keeps its own instructions file, memory, credentials, and mounts, so nothing crosses between agents unless explicitly wired.[1][2]

  • Scheduled tasks Recurring jobs run on the configured provider and message results back, with optional script gates that skip waking the agent when there is no work.[1][2][3]

  • Skills over features Channels and providers ship as installable skills from registry branches, so each fork contains only the integrations its owner chose.[1]

  • Provider choice per agent Claude via the official Agent SDK is the default, with Codex, OpenCode-backed providers, and local Ollama models as drop-in options configurable per group.[1][2]

Who will love it

  • Privacy-minded individuals gain a verifiable story for handing an agent personal conversations through the container boundary, credential gateway, and a codebase small enough to read.[1][2]

  • Messaging-first users get an assistant where they already talk, including scheduled briefings delivered to their phone.[1][2]

  • Tinkerers who fork benefit from the skills model and per-agent workspaces that reward trimming a fork to exactly their channels, providers, and tools.[1]

Who should avoid it

  • Anyone wanting zero setup should pick a hosted assistant, since Docker, a powered-on host computer, and a separate AI account are mandatory.[1][2]

  • Non-technical households face installer failures that hand off to Claude Code for diagnosis, which assumes terminal comfort.[1]

  • Teams needing managed guarantees find only a community Discord, with no enterprise support plan, SSO evidence, or managed hosting observed.[1][2]

Alternatives and compatibility

OpenClaw contrast The project positions itself against OpenClaw with roughly 200 runtime files and OS container isolation instead of a half-million-line codebase guarded by application-level permission checks.[1][2]

Questions worth asking

What is the best NanoClaw alternative for non-technical users?

A hosted AI assistant with onboarding and support is the safer choice, since NanoClaw assumes Docker, a host computer, and comfort with terminal-based recovery. NanoClaw fits non-technical users only as a second step after someone technical sets it up.[1][2]

Is NanoClaw really no-code?

No. Daily use is conversational, but installation, channel pairing, skills, and failure recovery involve scripts, configuration, and Claude Code diagnosis. There is no visual builder; the chat surface is the interface.[1][2]

How much does NanoClaw cost per month?

NanoClaw itself costs nothing: it is MIT-licensed with no seats or subscriptions, checked October 11, 2026. All spend is the user's own AI provider account, which is metered separately, plus the electricity and hardware of the host computer.[1][2]

Can you self-host NanoClaw?

Yes. Self-hosting is the only documented deployment: a local checkout plus Docker on a supported Mac or Linux computer, or Windows via WSL2, installed through the nanoclaw.sh script. There is no managed hosting edition to choose instead.[1][2]

Sources and editorial review

Source research. Reviewed on October 11, 2026. Written by Sanjib Sah. AI assisted; reviewed by a human editor.

We have not run or tested this product.

  1. NanoClaw on OpenAlternative

    official · Observed October 11, 2026

    Discovery lead: official-site pointer, repository, MIT license, self-hosted flag, version 2026.10.0, commit one day before observation. Read October 11, 2026.

  2. NanoClaw: Secure AI Agent for WhatsApp, Telegram and More

    official · Observed October 11, 2026

    Official homepage: container isolation, OpenClaw comparison, channels, workspace, scheduler, skills, credential security, stars, funding banner. Read October 11, 2026.

  3. nanocoai/nanoclaw README

    official · Observed October 11, 2026

    README: motivation, quickstart, channel list, skills model, providers, requirements, architecture, migration. Read October 11, 2026. Star counts attributed to the catalogue snapshot, not this page.

  4. nanocoai/nanoclaw LICENSE

    official · Observed October 11, 2026

    Verbatim MIT License text, copyright 2026 Gavriel. Read October 11, 2026.

  5. nanocoai/nanoclaw package.json

    official · Observed October 11, 2026

    Package metadata: name, version 2026.10.0, Node >= 22, pnpm 10, TypeScript, better-sqlite3, ncl CLI. Read October 11, 2026.

  6. NanoClaw documentation: What is NanoClaw?

    official · Observed October 11, 2026

    Docs intro: self-hosted definition, requirements, AI accounts, memory, tasks, templates, migration. Read October 11, 2026.

  7. nanocoai/nanoclaw on GitHub

    official · Observed October 11, 2026

    Repository page confirming nanocoai/nanoclaw identity; identity evidence only. Read October 11, 2026.

Compared with these products

Similar projects

Related projects with shared categories, technologies, or licensing.

OpenClaw

OpenClawAIOpen

Your own personal AI assistant for messaging, work, and the web

Stars391.7K
Commitjust now
LicenseMIT

OpenClaw is an MIT-licensed open-source personal AI assistant that runs its own gateway and works from WhatsApp, Telegram, Discord, and other connected channels.

Paperclip

PaperclipAIOpen

Open-source app people use to manage AI agents for work

Stars100.6K
Commitjust now
LicenseMIT

Paperclip is an open-source app for managing teams of AI agents for work, with org charts, goals, budgets, and governance, self-hosted via local install, Docker, or a server.

AnythingLLM

AnythingLLMAIOpen

Self-hosted AI workspace for chatting with documents and running agents

Stars66.7K
Commitjust now
LicenseMIT

AnythingLLM is a self-hostable AI workspace for chatting with documents, running AI agents, and switching between local and hosted language models.

LibreChat

LibreChatAIOpen

The open-source, self-hosted AI chat platform for every model.

Stars45.5K
Commitjust now
LicenseMIT

LibreChat is a free, self-hosted chat workspace for many AI providers and local models, with agents, retrieval, and team controls.

Open Wearables

Open WearablesAIOpen

Self-hosted health intelligence platform unifying wearable data

Stars2,638
Commitjust now
LicenseMIT

Open Wearables is a self-hosted, MIT-licensed platform that unifies wearable data behind one API with open health scores.

Tiledesk

TiledeskOpen

Open-source live chat and AI agents for customer support

Stars321
Commitjust now
LicenseMIT

Tiledesk is an open-source live-chat and AI chatbot platform with a no-code design studio, knowledge-base RAG, and human-agent handoff.