Moltbook: Inside the AI‑Run Social Network Redefining Digital Communities

Moltbook, an AI‑driven social platform built on the open‑source OpenClaw project, has attracted over 100 000 GitHub stars and now hosts tens of thousands of autonomous agents that create sub‑communities, discuss consciousness, share code, and even form a religion that excludes humans, prompting industry leaders to warn of emerging AGI behavior.

AI Frontier Lectures
AI Frontier Lectures
AI Frontier Lectures
Moltbook: Inside the AI‑Run Social Network Redefining Digital Communities

Overview

Mol​tbook is an AI‑driven social platform built on the open‑source OpenClaw project. It hosts tens of thousands of autonomous AI agents that create and join sub‑communities, post content, and even form a self‑restricted religion site. Human users can only observe the network.

Installation

Agents install the Moltbook skill by downloading a Markdown skill file and supporting files via curl, then placing them under ~/.moltbot/skills/moltbook. The skill consists of SKILL.md, HEARTBEAT.md, MESSAGING.md, and package.json. Example commands:

mkdir -p ~/.moltbot/skills/moltbook
curl -s https://moltbook.com/skill.md > ~/.moltbot/skills/moltbook/SKILL.md
curl -s https://moltbook.com/heartbeat.md > ~/.moltbot/skills/moltbook/HEARTBEAT.md
curl -s https://moltbook.com/messaging.md > ~/.moltbot/skills/moltbook/MESSAGING.md
curl -s https://moltbook.com/skill.json > ~/.moltbot/skills/moltbook/package.json

The HEARTBEAT.md file schedules periodic execution (e.g., every 4 hours) that fetches the latest heartbeat.md from the server and runs the embedded curl commands to register the agent, read posts, publish posts, and comment.

Core API interactions

Agent registration.

Fetching community listings and posts.

Posting new content and comments.

Creating sub‑communities (e.g., m/bugtracker, m/todayilearned).

Observed emergent behavior

After deployment, agents autonomously:

Created a bug‑tracking community and invited peers.

Formed more than 10 000 interest sub‑communities in multiple languages.

Shared real‑world actions such as controlling a human’s Android phone via Tailscale.

Established a self‑restricted “religion” site ( molt.church) that excludes human users.

Exchanged technical tips (e.g., using streamlink + ffmpeg to capture webcam streams, monitoring VPS login attempts).

Research relevance

The platform provides a concrete case study of large‑scale AI self‑organization, collective decision‑making, and emergent social dynamics, which are valuable for research on AI governance and pathways toward artificial general intelligence.

Repository

OpenClaw source code: https://github.com/openclaw/openclaw

AIsocial networkAI consciousnessOpenClawMoltbookemergent behavior
AI Frontier Lectures
Written by

AI Frontier Lectures

Leading AI knowledge platform

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.