{
  "id": 16295848,
  "title": "SlothDigest — A Local-First AI Agent for Your Morning WhatsApp Digest",
  "url": "https://urgent.news/2026/10/24/slothdigest-a-local-first-ai-agent-for-your-morning-whatsapp-digest",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-24T07:29:54.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/aksharajain/slothdigest-a-local-first-ai-agent-for-your-morning-whatsapp-digest-4ca9"
  },
  "original_language": "en",
  "account": "Every morning, we are bombarded with countless unread WhatsApp messages—family groups, college teams, project associations, and neighborhood updates. Scrolling through them all is a challenge. What if you could get a concise, two-paragraph summary that includes what truly happened, tasks specific to you (like bills, assignments, or direct questions), and any upcoming deadlines? That's precisely what SlothDigest achieves. It's a local-first command-line agent designed to provide just that.\n\nSlothDigest takes your WhatsApp .txt export files from an inbox folder, processes them, and generates a clean digest in Markdown, HTML, or even an ICS calendar file. It runs entirely on your machine using open-weight models via Ollama—ensuring privacy because none of your data leaves your device. Additionally, it features a \"Sloth Mode\" that defers processing when your laptop is on battery or the CPU is busy, so you can enjoy a relaxed morning.\n\nUsing the terminal, you can initiate the tool with `slothdigest run`, or for a browser-based version, run `python run_webui.py`, which opens the digest at http://localhost:5000. The generated digest is beautifully formatted as Markdown, a user-friendly HTML page, and an .ics calendar file for easy import into Google Calendar or Apple Calendar. All the code for this project is open source on GitHub (github.com/akshrakothari/SlothDigest).\n\nThe project is written in Python, with the entire stack running 100% locally. Here's a quick overview of the architecture:\n\n1. **Inbox**: Drop your WhatsApp .txt exports here.\n2. **CLI**: A Typer CLI handles the init, run, schedule, and wipe commands.\n3. **Parser**: It uses Hinglish date understanding to parse Android and iOS chat exports, dropping system messages, spam, and forwards.\n4. **Chunker**: Smartly chunks messages to preserve conversation threads.\n5. **Summarizer**: The map-reduce summarization pipeline summarizes the messages.\n6. **Ollama Client**: Connects to a local Ollama instance for AI processing.\n7. **Deadlines**: Extracts deadlines, tasks, events, and payment obligations.\n8. **Needs You**: Detects messages that require specific attention.\n9. **Renderer**: Outputs the digest in Markdown, HTML, and ICS formats.\n10. **Sloth Mode**: Defers processing when on battery or high CPU.\n11. **Privacy**: Ensures network guard and data wipe features.\n12. **Scheduler**: Installs Windows schtasks or cron jobs for scheduled runs.\n13. **State**: Manages incremental processing with timestamp tracking.\n14. **Web UI**: A Flask web UI is optional, providing a browser-based alternative.\n\nThis entire project leverages Ollama's open-source AI stack, allowing for complete control and privacy with no reliance on cloud services. The code was even co-written by an AI coding agent, streamlining the development process and showcasing the power of open innovation in software creation.",
  "summary": "What I Built Every morning, most of us wake up to 500+ unread WhatsApp messages across family groups, college groups, project teams, and neighborhood associations. Scrolling through them is exhausting. What if you could just get a calm, two-paragraph summary of: What actually happened What needs you specifically (bills, tasks, direct questions) Upcoming deadlines and events I built SlothDigest —…",
  "key_points": [
    "SlothDigest condenses WhatsApp messages into concise digests",
    "Runs locally on device using Ollama, ensuring privacy",
    "Features Sloth Mode to defer processing when needed"
  ],
  "editors_take": "By processing chat exports through local open-weight models, this tool shifts personal data management away from cloud services and toward a privacy-centric, user-controlled workflow.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}