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

About the project

NanoClaw is an AI assistant that runs agents inside separate Linux containers, isolating their files and execution environments. People use it to connect agents to messaging services and run assistants with memory and scheduled jobs. The catalogue contains skills and instructions for extending or operating NanoClaw.

This repository also configures its own agents. See what nanoclaw tells them →

31kStars on the repository
66Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

add-anydoc

01

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

not rated 31k +52 today C SkillSpector: warn 64 tokens original MIT

nanocoai/nanoclaw

Skill Claude Code

Convert an attached Word document, presentation, spreadsheet, OpenDocument file, RTF, EPUB, CSV, or text-based PDF into local Markdown. Use when a message supplies a local attachment path that must be read without uploading it to an external parser.

not rated 31k +52 today A Snyk: passSkillSpector: pass 57 tokens original MIT

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

not rated 31k +52 today A Snyk: failSkillSpector: warn 33 tokens original MIT

add-clidash

04

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group…

not rated 31k +52 today A Snyk: passSkillSpector: warn 87 tokens original MIT

add-codex

05

nanocoai/nanoclaw

Skill Claude Code needs its repo

Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via ncl groups config update --provider codex. Distinct…

not rated 31k +52 changed 5d ago A Snyk: passSkillSpector: pass 92 tokens original MIT

add-dashboard

06

nanocoai/nanoclaw

Skill Claude Code

Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

not rated 31k +52 today A Snyk: failSkillSpector: warn 32 tokens original MIT

add-deltachat

07

nanocoai/nanoclaw

Skill Claude Code

Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

not rated 31k +52 today A Snyk: failSkillSpector: warn 38 tokens original MIT

add-dial-number

08

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add another phone number to an existing Dial channel — a second (or third) public line for the agent, so one NanoClaw install answers SMS and AI voice calls on multiple numbers. Use when Dial is already installed and the operator wants an additional number (e.g. a personal line plus a support line). Requires the Dial…

not rated 31k +52 today A Snyk: passSkillSpector: pass 83 tokens original MIT

add-dial-tool

09

nanocoai/nanoclaw

Skill Claude Code needs its repo

Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…

not rated 31k +52 changed 6d ago A Snyk: failSkillSpector: warn 117 tokens original MIT

dial-cli

10

nanocoai/nanoclaw

Skill Claude Code

Reference for the dial CLI — gives you a real phone number to send SMS, place AI voice calls, and receive inbound texts/codes via the Dial platform (getdial.ai). Use when the user mentions phones, calls, texts, SMS, voice, OTP, 2FA, or verification codes; when they ask to text, call, ring, or wait for a code from…

not rated 31k +52 today A Snyk: passSkillSpector: warn 149 tokens original MIT

add-dial

11

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add Dial channel integration — a real phone number for SMS and AI voice calls via the Dial platform (getdial.ai). Native adapter — no Chat SDK bridge.

not rated 31k +52 today D SkillSpector: warn 36 tokens original MIT

add-discord

12

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add Discord bot channel integration via Chat SDK.

not rated 31k +52 today B SkillSpector: warn 13 tokens original MIT

add-emacs

13

nanocoai/nanoclaw

Skill Claude Code

Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed.

not rated 31k +52 today A Snyk: passSkillSpector: warn 55 tokens original MIT

add-gchat

14

nanocoai/nanoclaw

Skill Claude Code

Add Google Chat channel integration via Chat SDK.

not rated 31k +52 today A Snyk: passSkillSpector: pass 13 tokens original MIT

add-github

15

nanocoai/nanoclaw

Skill Claude Code

Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.

not rated 31k +52 today A Snyk: failSkillSpector: warn 21 tokens original MIT

add-imessage

16

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add iMessage to NanoClaw — one channel, two backends. Local (this Mac's chat.db via the Chat SDK bridge; macOS + Full Disk Access) or Hosted iMessage (via photon.codes — native spectrum-ts with a device-login wizard; any OS, no Mac relay). Triggers on "add imessage", "connect imessage", "add photon", "imessage via…

not rated 31k +52 changed 11d ago A Snyk: passSkillSpector: warn 92 tokens original MIT

nanocoai/nanoclaw

Skill Claude Code

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

not rated 31k +52 today A Snyk: passSkillSpector: warn 56 tokens original MIT

add-linear

18

nanocoai/nanoclaw

Skill Claude Code

Add Linear channel integration via Chat SDK. Issue comment threads as conversations.

not rated 31k +52 today A Snyk: failSkillSpector: pass 17 tokens original MIT

add-macos-statusbar

19

nanocoai/nanoclaw

Skill Claude Code

Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.

not rated 31k +52 today A Snyk: passSkillSpector: warn 49 tokens original MIT

add-matrix

20

nanocoai/nanoclaw

Skill Claude Code

Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.

not rated 31k +52 today A Snyk: failSkillSpector: warn 19 tokens original MIT

add-mattermost

21

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add a self-hosted or cloud Mattermost bot channel through the Chat SDK bridge, reusing a healthy server when available and linking to official server setup guidance when needed.

not rated 31k +52 changed 6d ago D SkillSpector: warn 39 tokens original MIT

add-ollama-provider

22

nanocoai/nanoclaw

Skill Claude Code

Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with…

not rated 31k +52 today C SkillSpector: warn 88 tokens original MIT

add-ollama-tool

23

nanocoai/nanoclaw

Skill Claude Code needs its repo

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

not rated 31k +52 today A Snyk: passSkillSpector: warn 28 tokens original MIT

add-opencode

24

nanocoai/nanoclaw

Skill Claude Code needs its repo

Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via ncl groups config update --provider opencode; host passes OPENCODE and XDG mount when spawning containers.

not rated 31k +52 changed 16d ago A Snyk: passSkillSpector: warn 65 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: