Sloth Digest 🦥 — a local Gemma 3 agent that does my inbox triage so I don't have to

A developer built Sloth Digest, a local email-triage agent that runs Gemma 3 4B IT (QAT-quantized) on llama.cpp over plain CPU to sort unread Gmail into urgency buckets and produce a morning markdown digest. The roughly 200-line Python stdlib pipeline uses a strict three-line CATEGORY/SUMMARY/ACTION verdict at temperature 0, fetches mail read-only via the Gmail API, and processes six sample emails in about 14 seconds without any cloud API. The developer says nothing leaves the machine: "Pull the network cable and it still works.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady https://dev.to/challenges/hacktoberfest-week3-2026-10-19 Sloth Digest is a local AI agent that reads my unread Gmail overnight and hands me a morning digest, so I never have to open a cold inbox again. Every email gets triaged by an open-weight model running entirely on my own machine Gemma 3 4B IT, QAT-quantized, served by llama.cpp on plain CPU into three buckets: Who gets to be lazier? Me, every single morning. Instead of 15–30 minutes of scanning subject lines and context-switching, I read one short markdown page and only touch the 3–4 emails that actually need a human. Here's real output from the bundled sample inbox: 🦥 Sloth Digest — morning triage ⚡ Needs you 4 - Energia Lux — Your October invoice — €84.12 due Oct 27 Electricity bill of €84.12 is due soon. → Pay the invoice before October 27th. - Marco Silva — Re: Thursday moved to 15:00? Plumber availability needs confirmation for Thursday. → Confirm 15:00 or propose an alternative time. ... 😴 Skip safely 1 - ShopMega — 🔥 70% OFF ends tonight — don't miss out Promotional email about a limited-time sale. 6 emails triaged locally in 14s ~12 min of manual triage saved . Nothing left this machine. Live demo: https://friend-crops-sharp-episode.trycloudflare.com https://friend-crops-sharp-episode.trycloudflare.com It shows the sample inbox 6 fake emails — bills, a friend asking for a confirmation, a flash sale, a delivery notice, a medical appointment reminder and runs the triage live on the local Gemma model when you hit the button. ~14 seconds on CPU, no cloud API involved anywhere. You can reproduce the whole thing offline: ./llama-server -m gemma-3-4b-it-qat-Q4 0.gguf --port 8801 python sloth digest.py --demo sample inbox, zero credentials needed A local AI agent that reads your unread Gmail overnight and hands you a morning digest — so you don't have to. Every email is triaged into three buckets by an open-weight model running entirely on your own machine Gemma 3 4B IT QAT via llama.cpp : No email content ever leaves your computer. Works offline. Costs nothing per run — set it up once and forget it. Your inbox is the most private dataset you own. A closed API means sending every message — invoices, medical appointments, personal threads — to someone else's servers. Sloth Digest runs the whole pipeline against a local OpenAI-compatible endpoint, so the "open" piece is the product: The agent is ~200 lines of Python stdlib. The only dependencies are llama.cpp for inference and, for the optional web UI, FastAPI. The architecture is deliberately boring — a sloth would approve: unread Gmail ──► fetch Gmail API, strictly read-only │ ▼ ┌─────────────────────┐ │ Gemma 3 4B IT QAT │ per email: CATEGORY / SUMMARY / ACTION │ llama.cpp, CPU │ strict 3-line verdict, temperature 0 └─────────────────────┘ │ ▼ morning digest markdown, grouped by urgency Three design choices make a small 4B model reliable enough to trust with triage: CATEGORY / SUMMARY / ACTION at temperature 0. No essays, no JSON to break. Local inference is not a gimmick here, it's the point: the whole pipeline — fetch, classify, summarize — runs against llama.cpp's OpenAI-compatible endpoint on 127.0.0.1 . Pull the network cable and it still works. Your inbox is probably the most private dataset you own: invoices, medical appointments, family threads, business negotiations. Triage means reading all of it — and with a closed API, "reading" means shipping every message to someone else's servers, on someone else's terms, under a privacy policy that can change. Because Gemma's weights are open and llama.cpp is open source, the equation flips: I ran it on my real unread inbox this morning: 8 emails triaged in ~20 seconds , and the digest correctly separated two things I genuinely needed to act on from the newsletter noise. Manual triage averages ~2 minutes per email once you include the context-switching — so the agent saves me roughly 15 minutes a day, ~90 hours a year , for a one-time setup cost and €0 in API fees. The cron job runs at 7am. I wake up, read one page, and go back to being lazy. The sloth wins. 🦥