LettaBot

Cross-Platform Personal AI Assistant - Unified Memory

LettaBot is a cross-platform personal AI assistant featuring unified memory that persists across Telegram, Slack, WhatsApp, and Signal. With LettaBot, your AI remembers conversations, preferences, and context no matter which platform you use, creating a seamless AI assistant experience. GitHub: https://github.com/letta-ai/lettabot Developer: letta-ai (Community Open Source) License: MIT Platforms: Telegram, Slack, WhatsApp, Signal, Web Key Innovation: LettaBot solves the fragmentation problem of AI assistants by maintaining unified memory across all your communication platforms, so your AI truly knows you regardless of where you interact.

Core Philosophy: "One AI, everywhere you are - with memory that never forgets"

Why LettaBot?

Unified Memory: Your AI remembers everything across all platforms.

Multi-Platform: Works on Telegram, Slack, WhatsApp, and Signal.

Persistent Context: Conversations continue seamlessly across platforms.

Privacy Control: You control what's remembered and what's forgotten.

Key Features

$#1.
Unified Memory System

• Cross-platform memory sync
• Persistent conversation history
• User preference storage
• Context retention
• Memory search and retrieval

$#2.
Platform Support

• Telegram: Full bot integration
• Slack: App and DM support
• WhatsApp: Business API
• Signal: Bot integration
• Web: Direct chat interface

$#3.
Memory Features

• Long-term memory storage
• Short-term context window
• Memory prioritization
• Forgetting mechanism
• Memory export/import

$#4.
User Profiles

• Multi-user support
• Profile customization
• Preference learning
• Usage analytics
• Privacy settings

$#5.
Privacy Controls

• Memory deletion
• Data export
• Incognito mode
• Selective memory
• Encryption options

Installation

Docker (Recommended)

# Pull image
docker pull lettaai/lettabot:latest

# Create config
mkdir -p ~/lettabot/config
mkdir -p ~/lettabot/data

# Run container
docker run -d \
  --name lettabot \
  -v ~/lettabot/config:/app/config \
  -v ~/lettabot/data:/app/data \
  -p 8080:8080 \
  lettaai/lettabot:latest

Python Installation

# Clone repository
git clone https://github.com/letta-ai/lettabot.git
cd lettabot

# Create virtual environment
python -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Configure
cp config.example.yaml config.yaml
# Edit config.yaml

# Run
python main.py

Node.js Installation

git clone https://github.com/letta-ai/lettabot.git
cd lettabot
npm install
npm run build
npm start

Configuration

config.yaml

platforms:
  telegram:
    enabled: true
    bot_token: ${TELEGRAM_BOT_TOKEN}
  
  slack:
    enabled: true
    bot_token: ${SLACK_BOT_TOKEN}
    app_token: ${SLACK_APP_TOKEN}
  
  whatsapp:
    enabled: false
    phone_number: ${WHATSAPP_PHONE}
    api_key: ${WHATSAPP_API_KEY}
  
  signal:
    enabled: false
    phone_number: ${SIGNAL_PHONE}
    service_url: http://localhost:8081

memory:
  provider: sqlite
  path: ./data/memory.db
  max_memories: 10000
  retention_days: 365

ai:
  provider: openai
  model: gpt-4o-mini
  api_key: ${OPENAI_API_KEY}

privacy:
  encryption: true
  auto_delete: false
  export_enabled: true

Usage

Telegram

1. Create bot via @BotFather
2. Get bot token
3. Add to config.yaml
4. Restart LettaBot
5. Start chatting with your bot

Slack

1. Create Slack app
2. Add bot permissions
3. Install to workspace
4. Add tokens to config
5. Invite bot to channels

Memory Commands

/memory search <query>  - Search memories
/memory delete <id>     - Delete specific memory
/memory export          - Export all memories
/memory clear           - Clear all memories
/status                 - Show memory stats

Pricing

Free: LettaBot is completely free and open source under MIT license. You only pay for:

• AI model API usage
• Platform fees (WhatsApp Business API)
• Server hosting (if self-hosting)

System Requirements

Use Cases

Personal AI Assistant

Have a personal AI that remembers your preferences and history across all platforms.

Multi-Platform Conversations

Start conversations on Telegram and continue on Slack seamlessly.

Team Communication AI

Deploy as a team assistant that remembers project context and decisions.

Customer Support Bot

Provide consistent support experiences across multiple channels.

Memory-Augmented Chat

Enable AI conversations that build on previous interactions.

Cross-Platform Automation

Automate tasks across multiple communication platforms.

Community and Support

• GitHub: https://github.com/letta-ai/lettabot
• Documentation: https://github.com/letta-ai/lettabot#readme
• Issues: GitHub Issues tab
• Discussions: GitHub Discussions tab

Quick Start Guide

Get LettaBot up and running quickly.

Step 1: Install

cd lettabot
npm install
npx lettabot setup

Step 2: Configure

Set your AI model and API key in the configuration.

Step 3: Connect and Go

Link your messaging platform and start using your AI agent.

Full documentation: https://github.com/letta-ai/lettabot#readme

FAQ

Is LettaBot free to use?

Yes, LettaBot is free and open source (MIT license). You only pay for AI model API costs if using external models.

What are the system requirements for LettaBot?

LettaBot requires 512MB RAM of RAM minimum. Runtime: Python/Node.js. It runs on Windows, macOS, and Linux.

Can I self-host LettaBot?

Yes. LettaBot is open source (MIT) and can be self-hosted on your own hardware. Clone the repository from GitHub and follow the installation guide.

What platforms does LettaBot support?

LettaBot supports: Whatsapp, Telegram, Slack, Signal. Check the official documentation for the most up-to-date list of supported platforms.

How does LettaBot compare to OpenClaw?

LettaBot offers a different approach compared to OpenClaw. While OpenClaw provides the largest ecosystem with 13,729+ skills and maximum flexibility, LettaBot focuses on personal assistant. Choose LettaBot if you prioritize its specific features; choose OpenClaw for the broadest compatibility and community support.

Is LettaBot suitable for beginners?

LettaBot requires some technical knowledge to set up (Python/Node.js). If you are a beginner, consider starting with QClaw (one-click install) or MaxClaw (cloud-based, no setup) first, then graduate to LettaBot as you gain experience.

License

MIT License - Free for personal and commercial use.

Tags

ai-agent, cross-platform, memory, telegram, slack, whatsapp, signal, persistent