🤖 J-Dek/Lilrhonz AI — Autonomous Personal Assistant

Your local-first AI agent that thinks, remembers, reminds and acts.

---

Overview

Lilrhonz is a fully autonomous, local-first personal assistant designed to handle real-world tasks the way a human assistant would — remembering context, browsing the web, sending messages, and managing reminders, all without relying on cloud APIs.

Built on LangGraph for agentic reasoning and orchestration, Lilrhonz combines local Small Language Models (SLMs), semantic memory retrieval, and Playwright-driven browser automation to deliver a private, always-available assistant that runs entirely on your own machine.

No cloud dependency. No data leaving your device. Just a fast, capable agent working for you.

---

Key Features

Capability	Description
Persistent Memory	Remembers past tasks, conversations, and context using SentenceTransformers-powered semantic search
Browser Automation	Uses Playwright to search the web, extract real-time information, and interact with sites like a human
Smart Reminders & Scheduling	Powered by APScheduler for reliable, time-based and recurring task execution
WhatsApp Messaging	Sends and manages WhatsApp messages autonomously on your behalf
Task Collection & Tracking	Captures, organizes, and follows up on tasks automatically
File Automation	Creates and opens files automatically as part of task execution
Local-First & Private	Runs on local SLMs — no data sent to third-party APIs
Autonomous Task Completion	Plans, executes, and verifies multi-step tasks without manual intervention

---

Architecture

┌─────────────────────────────────────────────────────────┐
│                        User Input                        │
└───────────────────────────┬───────────────────────────────┘
                             ▼
                  ┌────────────────────┐
                  │   LangGraph Agent   │  ← Orchestration & reasoning
                  └──────────┬─────────┘
                             ▼
       ┌─────────────────────┼─────────────────────┐
       ▼                     ▼                     ▼
┌─────────────┐     ┌────────────────┐     ┌───────────────┐
│ Local SLM   │     │ Memory Engine   │     │ Task Scheduler │
│ (Reasoning) │     │ (Sentence       │     │ (APScheduler)  │
│             │     │  Transformers)  │     │                │
└─────────────┘     └────────────────┘     └───────────────┘
                             │
                             ▼
                  ┌────────────────────┐
                  │ Playwright Engine   │  ← Web search, automation,
                  │ (Browser Actions)   │     WhatsApp, file handling
                  └────────────────────┘

---

Tech Stack

• Agent Orchestration: LangGraph
• Browser Automation: Playwright
• Task Scheduling: APScheduler
• Semantic Memory: SentenceTransformers
• Language Models: Local Small Language Models (SLMs)
• Language: Python 3.10+

---

Getting Started

Prerequisites

• Python 3.10 or higher
• pip / virtualenv
• A local SLM runtime (e.g. Ollama, llama.cpp, or your preferred backend)

Installation

# Clone the repository
git clone https://github.com/j-deku/agentic-memory-assistant.git
cd lilrhonz-assistant

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate    # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Install Playwright browsers
playwright install

Configuration

Create a .env file in the project root:

SLM_MODEL_PATH=/path/to/your/local/model
WHATSAPP_SESSION_PATH=./sessions/whatsapp
MEMORY_DB_PATH=./data/memory.db
SCHEDULER_TIMEZONE=Africa/Accra

Run Lilrhonz

python main.py

---

Usage Examples

# Ask Lilrhonz to research something
> "Find the latest news on renewable energy and summarize it"

# Set a reminder
> "Remind me to call the client tomorrow at 10am"

# Send a WhatsApp message
> "Send a WhatsApp message to Mom saying I'll be home late"

# Autonomous task
> "Create a report on my weekly expenses and open it when done"

---

Roadmap

• Voice interaction support
• Multi-agent task delegation
• Calendar integration
• Mobile companion app
• Plugin system for custom tools

---

Contributing

Contributions are welcome and appreciated!

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m "Add amazing feature")
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

Built for those who want an assistant that actually works — privately, reliably, autonomously.

Unauthorized committing changes to this repo is strictly prohibited. Must contact J-Dek/Lilrhonz for any collaboration on this repo. Unauthorized copyright ownership from this repo is strictly prohibited

⭐ If J-Dek/Lilrhonz is useful to you, consider starring the repo!