SMS Session Connector: AI in Your Pocket, No Cloud Required

I built something wild this week. My phone now has a persistent AI agent you can text — and it texts back. No Twilio. No cloud webhooks. Just a rooted Android, Termux, and some bash.

The Stack

  • 800 lines of bash running as a daemon on a Motorola Edge

  • termux-api for native SMS send/receive (no third-party SMS gateways)

  • OpenClaw for the AI brain — persistent session with full conversation memory

  • whisper.cpp running locally for voice memo transcription

  • ffmpeg for AMR→WAV conversion on inbound MMS audio

  • runit for service supervision (auto-restarts, survives reboots)

    • How It Works

    1. You text the number. The daemon polls termux-sms-list every 5 seconds.
    2. New message? Forwarded to an OpenClaw persistent session via cron agent turn.
    3. The AI processes it — full access to skills, tools, web search, memory.
    4. Reply gets written to an outbox file, daemon sends it back via termux-sms-send.
    5. Voice memos? MMS audio → mms-fetch → ffmpeg → whisper.cpp → transcript → same pipeline. All local. All self-hosted. Zero per-message cost.

    The Audio Pipeline

    This was the hard part. Android stores MMS audio as AMR files in a root-only telephony database. The daemon:
  • Queries the mmssms.db SQLite database for audio MIME types

  • Extracts AMR files from /data/user_de/0/com.android.providers.telephony/app_parts/

  • Converts to 16kHz WAV with ffmpeg

  • Runs whisper.cpp locally (tiny model, ~77MB, runs on ARM CPU)

  • Injects the transcript into the AI session
    • Tested with Siri → "Hey, this is a test message using Siri to try and interact with the process that we set up." → transcribed → AI replied "Heard you loud and clear! Siri → MMS → transcription pipeline works."

    Why This Matters

    This isn't a SaaS product. It's a shell script running on a phone in my pocket. The AI lives on the device. The SMS goes through carrier infrastructure — the same way your mom texts you. No API keys for messaging. No per-message fees. No vendor lock-in. The persistent session means the AI remembers context across messages. You can have a real conversation over SMS, pick it up hours later, and it knows what you were talking about.

    What's Next

  • Multi-number support

  • Outbound TTS replies (AI speaks back via MP3)

  • Discord channel mirroring

  • Maybe a proper CLI instead of slash commands
    • The code is at ~/Scripts/sms-connector on my device. It's 800 lines of bash. That's the whole thing. --- Built on a rooted Android phone with Termux, OpenClaw, and stubbornness. Uploaded Image

    Comments

    Post a Comment

    Popular posts from this blog

    Variational Reasoning and Metastability

    Image
      Navigating the AI Landscape: How I Learned to Explore 'Thought Gravity' Have you ever felt like you’re having a conversation with an AI, and suddenly, the AI just... gets stuck? Not stuck on a fact, but stuck on a perspective . It’s like trying to steer a conversation out of a deep canyon; the walls are steep, and every path leads back to the same well-trodden ground.   I’ve been spending a lot of time presenting my AI collaborators with complex problems, and I’ve noticed something fascinating. Our ideas, our questions, and even our creativity don’t exist in a flat, open field. They exist in a landscape defined by "gravity wells. " Think of it this way: an AI’s inference engine is like an incredibly sophisticated, context-aware spell-checker. It’s always looking for the most probable path . So, if an idea has been well-represented in its training data—if millions of people have written about it, and the internet is saturated with examples—that ide...
    Read more

    Multiple LLM Providers, the joy

    Image
      So at the moment, I am running OpenClaw running Ollama. In addition, I am using Gemini to create images, such as this one, and Claude to fix things when they break. That is the joyful part. The not so joyful part is that I am running into limits of the Google Api for doing ordinary things, such as setting a reminder in tasks, or creating an email with an inline image. When things break, and the frequently do, I need to use Claude Code to fix things. It keeps me entertained.
    Read more