Moltbot

Overview

Moltbot is an open-source, self-hosted personal AI assistant that connects large language models like Claude and GPT to your existing messaging platforms. Built by Peter Steinberger and the community, it runs entirely on your own hardware—whether macOS, Linux, Windows (WSL2), or even a small cloud instance—prioritizing data privacy and local control over cloud-dependent alternatives.

The platform routes conversations from WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and more through a single WebSocket gateway. This architecture lets you manage multiple AI agents across different channels, automate recurring tasks with cron jobs, and execute shell commands or browse the web (with appropriate tool permissions and security configurations). Note that while configuration and workspace files stay local, using cloud-based models or external services will send request content to those providers—you can choose local models to minimize external data transmission. It's designed for developers, power users, and teams who want full ownership of their AI infrastructure without vendor lock-in.

Moltbot has gained significant traction with praise from tech reviewers like Federico Viticci of MacStories, who called it "the future of personal AI assistants." The platform enables you to clear your inbox, send emails, manage your calendar, check in for flights, and perform countless other tasks—all from WhatsApp, Telegram, or any chat app you already use. If you're comfortable with Node.js and command-line tools, Moltbot delivers a production-ready personal assistant that adapts to your workflow rather than forcing you into a hosted service.

Key Features

• Multi-Platform Messaging Integration — Connect WhatsApp, Telegram, Discord, Slack, Google Chat, Signal, iMessage, Microsoft Teams, and more to a single AI gateway, routing conversations to specialized agents without switching apps or managing separate bots. Most channels support DMs and group chats, though group chat policies, trigger methods (@mentions), visibility, and permissions vary by platform—refer to each channel's documentation for specifics.

• Persistent Memory — Supports cross-session context and memory files with session archives. You can persist preferences and information through workspace files and templates, creating controllable long-term context that evolves with your usage patterns.

• Browser Control & Web Automation — Launch and control dedicated Chrome/Chromium instances for web automation, fill forms, and extract data in an isolated agent-only browser. For sites with strong anti-scraping measures, login requirements, or high dynamic content, additional configuration or manual intervention may be needed. Perfect for automating repetitive web-based workflows.

• Full System Access — Run commands and access files with proper authorization. Tool capabilities can be restricted through tool policies, approval workflows, and sandboxing. This enables the assistant to perform actual tasks like managing your calendar, sending emails, or checking you in for flights.

• Dynamic Skills System — Extend functionality with community skills or build your own. The AI can even write its own skills, creating new capabilities on the fly. Skills are Markdown-based tool definitions that can be installed, updated, and shared through the community registry.

• Proactive Automation — Schedule recurring tasks with cron jobs, set up reminders, receive daily briefings, and enable background monitoring. The assistant can proactively check in during heartbeats and notify you of important updates or tasks that need attention.

Pricing & Plans

Moltbot itself is completely free and open-source under the MIT license. You can self-host it on any machine with Node.js 22+ at zero cost, paying only for the infrastructure you choose (your own hardware or a $5/month VPS) and the LLM API usage (charged by your selected provider such as Anthropic or OpenAI based on API consumption, not subscription fees).

Self-Hosting Costs:

• Software: Free (MIT license)
• Infrastructure: Your choice—local machine (free), cloud VPS ($5-20/month), or Raspberry Pi ($50 one-time)
• LLM API: Pay-as-you-go based on usage (Anthropic, OpenAI, or other compatible APIs)

Deployment Options:
You can self-host following the official VPS/cloud platform deployment guides, or use one-click templates from third-party platforms (such as Northflank). Self-hosting is recommended for maximum control and privacy.

Notes:

• The core Moltbot project has no licensing fees or subscription requirements.
• Self-hosting costs depend on your choice of hardware (local machine, cloud VPS, or Raspberry Pi-class devices).
• LLM costs are billed separately based on API usage by your chosen provider (e.g., Anthropic, OpenAI, or other compatible APIs according to their per-token pricing).

Best For

• Developers building personal automation workflows — If you want to script shell commands, automate cron jobs, or integrate AI into your existing tools without paying for cloud seats, Moltbot delivers full programmatic control over your assistant.

• Privacy-conscious individuals and teams — Organizations handling sensitive data (legal, healthcare, finance) can run Moltbot entirely on-premises or in a private VPC. By using local models and avoiding external services, you can minimize data transmission to third-party providers.

• Power users managing multiple messaging platforms — Route WhatsApp family chats, Telegram work groups, and Discord communities to different agent workspaces with isolated contexts, all from a single gateway dashboard.

• People who want an AI assistant that actually does things — Unlike traditional chatbots that only respond, Moltbot can perform real tasks like managing your calendar, sending emails, checking flights, and automating workflows—all from your phone via WhatsApp or Telegram.

• Researchers or hobbyists experimenting with multi-agent systems — The platform supports agent-to-agent messaging, spawning subtasks, and coordinating work across sessions, ideal for exploring agent orchestration patterns. For open-source alternatives, see Mastra AI.

FAQ