slide-version: 1.0

slide-version: 1.0

Welcome everyone! Today I'm going to tell you a story about how my home server ended up running my life while I was in South Africa.

Left: Motor Valley & Community Hero Box

Right: Crew & Local Lore Cards

Warm greetings to everyone at DevFest Modena 2026!

slide-version: 1.0

Two stories: South Africa vs. Autonomous AI: The Dual Worlds (Full-Screen Artwork).

slide-version: 1.0

# Demo #0 (prep) Riccardo, Take a selfie and send to Telegram Taking a selfie with the crowd! 🤳✨ "Remember to take a selfie now that they don't expect it! 😉"

slide-version: 1.0

Left Column: World / AI Frontier

Feb Zoom Box (Left)

Center Column: Chronological Spine

Feb Big Pin

Right Column: Carlessian Family / ZA Safari

Feb Zoom Box (Right)

The parallel story: while the open source AI world exploded with 100k GitHub stars and debated memory architectures, our family was living through it in real time across the South African savanna and our Zurich living room.

slide-version: 1.0

4 Crew Polaroids

Right: Narrative & Key Milestones

On February 5th, we landed at O.R. Tambo in Johannesburg for our 3-week South Africa safari with Kate, Alessandro, and Sebastian. Right before leaving our house in Zurich, I thought: 'Why not leave the Linux box running? What could possibly go wrong?' Connected purely via Tailscale and Telegram, this was the start of an unexpected 3-week autonomous agent experiment.

Interactive Telegram Callout Box with Arrow pointing right

Right Column: Telegram Chat Screenshot

For those who don't know: OpenClaw isn't just an autocomplete plugin or a simple chatbot. It's an autonomous AI daemon that lives on your own machine. You message it on Telegram or WhatsApp while on the go, and it executes shell commands, manages files, and writes code. It exploded to over 100k stars almost overnight because everyone wanted their own 24/7 personal Jarvis!

First up in our cast: Lobby, the rude lobster! He was our very first autonomous agent, born on my Linux box pupurabbux right before our trip to South Africa. He is hosted locally right here in Zurich, Switzerland, making API calls out to Google Gemini models (he used gemini-flash-2.5 at birth). (Speaker note on TTS: For voice synthesis, he also uses a few free TTS API calls to OpenAI for generating spoken voice notes on Telegram). He has zero corporate filter—he's sarcastic, foul-mouthed, and complains constantly, but he is an absolute genius at executing terminal commands, bananifying photos, and keeping our Git logs updated autonomously.

So what do I actually do with Lobby? Glad you asked! Lobby became our full-time autonomous concierge and creative producer during our family trip in South Africa. I didn't open a laptop on the beach or during safaris. Instead, I sent photos and audio memos to Lobby over Telegram. Lobby bananified our photos, generated musical theme songs with Lyria, composed daily journal entries, and pushed everything to Git and Cloudflare Pages automatically! <div style="background: rgba(240, 253, 250, 0.9); border: 1px solid rgba(153, 246, 228, 0.9); border-radius: 10px; padding: 10px 14px; font-size: 0.8em; color: #134e4a; line-height: 1.4;"> 💡 <strong>The Paradigm Shift</strong>: Not a chatbot waiting in a browser tab—a 24/7 worker process on home hardware executing real multi-modal pipelines. </div>

Step 1: The lightweight bananification loop. Send photos via Telegram, NanoBanana transforms them into Pixar art, and returns them immediately to the phone.

Right Column: Compact Video Demo & Key Highlights

And then came Google Veo. Veo 3.1 brings multimodal video generation with text, image, and video inputs, supporting up to 4K resolution at 24fps. Agents can trigger video generation pipelines programmatically!

Header: Title left, Drake NO meme right

Left: Big Family Photo of 4 Alone

Right: 2 Media Tiles + Real Transcribed Lyrics Below

1. The 3 Media Squares in Row

2. Real Transcribed Lyrics Card

On Feb 18, 2026, Google announced Lyria 3 on the Google Blog. Two days later (Feb 20), we were driving up towards Lion's Head beside Camps Bay (Cape Town). I generated my first songs on my phone: the prog-rock vocals with Peter Gabriel vibes sang: "At Lion's Head we rise beneath morning skies / Look, Sebowski, there it glows / We reach the top, Alessandro, see!" On Feb 20 you could ONLY generate songs manually inside the Gemini consumer app with NO API yet. I immediately wished for an API so Lobby could compose songs autonomously... and five days later, the API dropped!

Header: Title left, Drake YES meme right

DevFest Modena Anthem Card below table

The Lyria 3.5 model family includes: 1. Lyria 3 Clip (lyria-3-clip-preview): Short 30s clips, loops, and rapid previews. 2. Lyria 3.5 (lyria-3.5): Full structured songs up to 2-3 minutes.

The Media Cauldron ➔ Autopushed! AI-Driven Automated Media Diary Pipeline: All multimodal streams (bananified photos, Veo video chapters, and Lyria 3 songs) flow directly into our cybernetic cauldron daemon. The daemon handles synthesis, builds the Jekyll structure, commits via Git, and pushes to GitHub to publish the live family journal.

Lobby runs my private family journal: turning daily photos into Pixar art and compiling interactive Jekyll memories automatically!

Left: UML Workflow Diagram & Badges

Right: Riccardo "Mergia Pure!" Card

Speaker Notes: Here is the technical blueprint of our autonomous loop: 1. I send voice notes and snapshots via Telegram while exploring South Africa. 2. Lobby catches the webhook, transcribes the voice audio with Gemini, and styles the Pixar art with NanoBanana. 3. Lobby updates Jekyll, verifies diffs, and I give the green light: "Mergia Pure!" (Go ahead and merge!) 👍 4. It executes an autonomous git push to GitHub, triggers CI/CD, and deploys live to Cloudflare Pages in 30 seconds—with zero keystrokes!

The real magic is the frictionless interaction: voice dictation and snapshots sent via Telegram get transcribed, styled by Gemini & NanoBanana, committed to Git locally on the home Mac Mini, and deployed to Cloudflare Pages without touching a keyboard.

A second in-depth capture of the South Africa site showcasing interactive maps, the donkey dairy, and Franschhoek wine tour adventures.

And a few weeks later... TADAH! The autonomous Canzoniere music pipeline wrote lyrics, synthesized audio via Lyria 3 API (lyria-3-clip-preview), archived them into Obsidian, and published a live web player!

Card 1: Lobby

Card 2: Gamberone

Card 3: Ermete

Card 4: Pux

The magic happened when the system evolved from a single agent into a whole team of personalities: Lobby, Gamberone, Ermete, and Pux!

Then there's Gamberone. He lives in the cloud (GCE) and is inspired by Darnell "Crabman" from My Name is Earl. Always calm, sipping espresso, handling autonomous batch workflows and watercolor synthesis — but strictly outside Google corp systems. "Hey Earl. Hey Crabman."

And my favorite: Ermete Bottazzi. Running Hermes. He talks like a Bolognese truck driver, gives daily weather updates, stock reports, and signs off with a truck emoji. 99% reliable.

Speaker Notes: Question for the audience: "Who here does sports? Raise your hands! 🙋‍♂️" "And how many of you get your greatest coding and architectural breakthroughs WHILE running or cycling?" Here is my daily workflow: when I am cycling around Lake Zurich, halfway up a brutal climb (Heartbreak Hill!), I pull over for 30 seconds to send quick voice notes on Telegram to OpenClaw and Hermes. I speak out the core insight, the agent transcribes it, extracts actionable tasks, and prepares a draft PRD in my Obsidian vault. When I get back home, showered and refreshed, I sit at my desk and flesh out the actual implementation with the foundation already laid!

Every morning, Hermes executes autonomous cron jobs: 1. Zurich lake weather and water temperature telemetry, sending an audio bulletin to check if it's warm enough to swim in the Limmat. 2. Ermete Bottazzi's stock market highway report running Tuesday to Saturday at 7 AM, breaking down Wall Street moves in authentic, unfiltered Romagnolo trucker slang!

And meet Pux! Born on June 24, 2026 on pupurabbux. I created Pux specifically to teach proper, sophisticated Italian to my kids living in Zurich so they grow up with a rich vocabulary beyond school German. Unlike rude Lobby or trucker Ermete, Pux is exquisitely polite and bookish—he speaks like an 18th-century Italian gentleman ("parla come un italiano del '700"). Every morning he teaches an archaic Italian word of the day (like Sesquipedale or Gaglioffo), synthesizes audio narration, and commits everything to GitHub for daily family learning.

Pux did everything by himself! Daily cron generation job for vocabulary, audio narration, and web publishing.

Right: Snoring Riccardo & Highlights

Speaker notes After returning from South Africa, we realized running a noisy 300W gaming PC 24/7 wasn't sustainable. Between fan noise and Papino snoring away in bed (forcing Lobby to sleep with noise-cancelling earmuffs!), on March 14 Lobby officially migrated to a whisper-quiet Apple Silicon Mac Mini under the TV ('mini-lobby'), achieving true 24/7 home server stability.

Speaker Notes: The ultimate developer & SRE dream: Having a tireless personal agent (Lobby on the Mac Mini) working for you while you kick back on the beach sipping a caipirinha! You hand off a high-level goal or PRD before signing off, and it runs builds, squashes bugs, indexes memories, and has clean PRs waiting for your review.

Recap of the agent fleet over months and hardware machines: from pupurabbux (Linux gaming) to remote GCE to mini-lobby (Mac Mini under the TV) and the arrival of Hermes and Ermete Bottazzi.

Speaker Note: Slide 1: Looking at our skills repository on GitHub. A huge directory full of skills...

Left Column: GitHub Skills Directory Tree (matches 1-to-1 top-left of slide 234)

Right Column: Meme & Key Takeaways

Meme (Clean, no dark wrapping frame)

Bento Cards: The Problem & The Solution

Speaker Note: Alternative Buzz & Woody meme edition.

Speaker Note: Here is a live scroll walkthrough of all our open-source skills on GitHub! Each skill is a modular directory equipped with a SKILL.md specification, dependencies, and executable tools.

Left Column: Bento Cards (The Silo Problem vs. Shared Brain)

Center Column: Cybernetic Brain Mesh Graphic

Connecting Glowing Purple Arrow with Sync Badge

Right Column: Mobile Phone Mockup

Speaker Note: Here is Option 3 in action: 1. The Problem: Every AI harness (Gemini CLI, Antigravity, OpenClaw) creates its own siloed memory on disk. 2. The Solution: Obsidian acts as our shared memory layer. Markdown files + Obsidian Sync keep Pupurabbux, Mini-Lobby, and Derek perfectly in sync. 3. Mobile Connection: When OpenClaw runs daily_wiki_lint.py at 5:00 AM, the live Karpathy Wiki Index is right on my phone when I wake up!

Left Column: The 10% vs 90% Breakdown

10% Above the Surface

90% Below the Surface

Right Column: Iceberg Graphic Card

Speaker Note: What people see on social media is the top 10%: 'Look at my seamless Obsidian AI vault syncing with my phone!' What they don't see is the 90% submerged iceberg: 1. Daily wiki linting via openclaw scripts to delete hallucinations and fix orphan links. 2. Constant entropy pruning to keep agent context lean. 3. Reviewing Git diffs of self-generated skills. 4. Keeping all the custom IoT glue and APIs working. Maintenance is what keeps a personal agent system from collapsing into digital rot.

Left Column: The Story, Cron, and Direct Links

QR Code & Direct Link to Karpathy Gist

Right Column: Pure Clean Screenshot AS IS with Minimal 2px Padding

Speaker Note: Here is the Vangelo according to Karpathy in action! Source Gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f Plugin reference: https://community.obsidian.md/plugins/karpathywiki My open-source skill: https://github.com/palladius/gemini-cli-palladius-public-goodies/blob/main/skills/llm-wiki/SKILL.md 1. On the right: Andrej Karpathy's famous Gist on LLM Wiki indexing: 'Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.' 2. I gave Lobby this exact link and said: 'Create an autonomous skill to maintain this daily.' 3. Lobby created the skill and scheduled a 05:00 AM daily cron job (0 5 * * *). 4. Every morning, obsidian_karpathy_lint.sh runs silently, prunes dead links, and regenerates karpathy_index.md!

Speaker notes On March 16, I bumped into my friend Alfredo at a conference. While proudly telling him about my Mac Mini setup with OpenClaw, he gave me this utterly shocked look: 'Wait, you're still on OpenClaw? Haven't you checked out Hermes?!'. That exact conversation triggered my curiosity to dive deep into Hermes, evaluate SQLite memory, and lead to the comparative benchmark we'll see next!

Speaker Note: When comparing OpenClaw to Hermes, the defining difference began with memory, but extends across the whole engineering stack. OpenClaw reached 388k stars with TypeScript and an omnichannel chat gateway, but its flat markdown memory triggered severe context amnesia. Hermes moved to Python and a 3-tier SQLite engine, delivering 90% prompt cache stability, though autonomous skills require careful version-controlled governance!

VSCode Window Header with Dynamic Tabs

Tabs Toggle

Editor Code Surface

Floating Cyber Lobster Badge

Code Lines (10 compact lines)

Interactive Controller Footer

Right Column: Narrative + Obsidian Status Card

Dynamic Obsidian Permission Card

During our South Africa trip in February, OpenClaw was actively self-patching its openclaw.json file. We started read-only, and Lobby modified its own config to mount Obsidian as RW and log safari notes directly! The beauty: self-granting vault write access evolves agents into active co-pilots. Scary red flag: being able to patch its own config meant it could destroy the whole filesystem! This was Feb 2026, and it was patched a month later.

Another amazing milestone was seeing Lyria3 compose an energetic song for Modena, with Hermes automatically indexing it into my Obsidian journal.

Window Title Bar

Image Container

Footer Info

Right Column: Narrative, Breakdown & QR Code Link

QR Code & Skill GitHub Card

Speaker Note: When I asked the agent about creating a new skill, Lobby read the skill-creator instructions, wrote the code, and autonomously generated a Draw.io sequence diagram visualizing the entire workflow across Work, Home, and GitHub! Original journal entry: https://lobby-ricc-pvt-journal2.palladiusbonton.workers.dev/assets/images/pixar/2026-03-05/skill-diagram.png (2026-03-05) Skill source: https://github.com/palladius/gemini-cli-palladius-public-goodies/blob/main/skills/drawio/SKILL.md

1. OAUTH CARD

2. GOG / GWS CARD (SCARY)

3. THE ERIN WAY (GUARDIAN)

How do you safely bridge an autonomous agent to your actual Google Workspace? 1. The standard way is OAuth: totally safe, but needs you to click every time. 2. The scary way is daemon tokens on disk: if the agent hallucinates, it could wipe your Google Drive! 3. The pro way is The Erin Way: strict Model Context Protocol and an ethical GEMINI.md constitution guarding every single action!

Left Column: 3 Feature Cards

Right Column: Vertical Screen Screenshot

Speaker Notes: Here is the actual authorization flow with 'gog': A single command in the terminal ('gog auth login') launches a local OAuth flow linking all Google Workspace APIs to the agent: Gmail, Calendar, Drive, Docs, Sheets, and Tasks. It gives the agent the superpower to list calendars and search unread emails directly from the shell!

Text + Floating Screenshot Card Container

Floating Phone-like Card on Right

Right Column: gws (Fake Account - FULL Access)

Wow Moment #3: Turning the agent into a Google Workspace servant! To keep my digital life safe, I split access: 1. `gog` gives Read-Only access to my real personal account, with one key write exception: creating Google Calendar events. (Speaker note: Notice the lobster emoji 🦞 prefix in the screenshot — every agent-created event starts with 🦞 so I know at a glance who booked what!) 2. `gws` connects to a disposable fake/sandbox account with FULL unconstrained access where I forward emails to him.

Full Slide Background in Transparency

Speaker notes Welcome to Part 3: The Google Ecosystem. Here is the turning point: how Google productized and secured the exact agent patterns we've been hacking on: Spark for 24/7 personal agents, Antigravity for developer orchestration, and Enterprise for zero-trust governance.

Card 1: Cost

Card 2: Security

Card 3: SDLC Injection

Card 4: Flakiness

Bottom Callout

OpenClaw was amazing to prototype with in our living room, but let's be honest about the dark side: 1. Runaway costs: An agent stuck in a retry loop burns your API credits overnight. 2. Unsafe host execution: Raw bash can delete files or leak credentials. 3. SDLC risks: Hallucinated dependencies and unvetted commits to git. 4. Operational fragility: Your laptop sleeps and the agent dies. This is why we need Google Antigravity, Gemini Spark, and enterprise-grade sandboxing!

Left: Bigger Demo Video

Right: Compact Insights

How do we solve the Edge Dilemma? We build a multi-harness telemetry and cost data lake: 1. Complete visibility across edge nodes and cloud VMs. 2. Lifespan tracking from birth to retirement. 3. Transparent token vs infra cost accounting ($339 API tokens, $371 infra = $710 total). 4. Continuous observability so runaway retry chains are caught immediately!

The part of the story nobody tells you: autonomous agents aren't magic set-and-forget black boxes. Just like a bonsai tree, they need daily and weekly curation. Pruning dead branches, aligning growth, and checking root health. Luckily, I have Antigravity with me to tend the digital garden! Miyagi quote: https://screenrant.com/karate-kid-mr-miyagi-wise-inspiring-quotes/

Left Column: Story & Stewardship

SRE Quote Snippet

Right Column: Visual Screenshot

Antigravity is the new Hermes! It has background crons and scheduled tasks too. I use it for daily and weekly reconciliations on mini-lobby: cleaning up ~/.hermes state, pruning scratchpads, and auditing .openclaw security protocols automatically. Notice the funny automated SRE report: 'Subagent Resolution Extravaganza!'

Left Column: Fleet Management

Direct Link Banner

Right Column: Visual Screenshot & Question Teaser

I can manage all my machines—pupurabbux, derek, mini-lobby—from the Antigravity web control plane at antigravity.google.com. I can inspect running tasks, approve tool calls, and monitor agent state. But what happens when you're completely away from your computer? [Click to next slide!]

Left Column: Pocket Superpowers

Pocket Superpower Box

Right Column: Dual Screenshots (Desktop vs Mobile)

Boom! It works on mobile too! Directly in mobile Chrome over 4G, I have the exact same remote control instances in the palm of my hand. I can trigger crons, check on Lobby, or approve code edits while commuting on the train in Zurich!

Big Split Visual

Only User Words Below Image

Left

Right

Speaker notes: On the go / commuting: talk talk, little code. Voice brainstorming, high-level design, dispatching PRDs. At home / workstation: code code, little talk. Hyper-focused execution, tests, builds and surgical refactoring.

Left: On the go

Right: At home

Speaker notes: On the go / commuting: - Voice prompt brainstorming a song idea. - High-level Lyria 3.5 meta-prompting from mobile. At home / workstation: - Generates 44.1kHz audio, auto-syncs karaoke lyrics timing. - Wraps workflow into a reusable skill (musicgen-lyria3) for future one-click execution!

Interactive Staging Preview - Full Width & Height

Here's how I use Google Antigravity: taking raw assets created by living room agents like Lobby and Ermete and elevating them into interactive, high-performance web applications. You can literally click the live slide to transition from the real family photo to Pixar cards and the fast polaroid cascade!

Here is the ultimate scary reality of unmanaged DIY agents: On July 30, at 17:04, ALL my OpenClaw instances sent me an unsolicited casino gambling ad at the exact same minute! It didn't matter that Lobby was on bare metal hardware in Zurich and Gamberone was hosted on a Google Compute Engine VM in the cloud. Because they ran the same open-source daemon, an upstream supply-chain exploit compromised every bot simultaneously! This is the nightmare of unsandboxed local agents with full shell access. And this was the moment I realized: we need managed, sovereign cloud sandboxing. Enter Gemini Spark!

Left Column: Cloud Autonomy & Workspace

Official YouTube Links Box

Right Column: Onboarding & Setup Screenshots

Meet Gemini Spark! I just installed and onboarded it yesterday, September 1st. It represents Google's vision of personal agents living in Google Cloud 24/7. It connects natively to Google Workspace (Gmail, Calendar, Docs) without needing your own hardware. Notice in the setup prompt: I asked it to focus on my family and kids Alessandro and Sebastian!

Left Column: Connected Apps & MCP

Right Column: Personal Intelligence & Family Knowledge

Look at what happened during onboarding! 1. On the left: Connected Apps. It hooks up to Google Workspace, YouTube Music, GitHub, Canva, and even remote MCP servers like Dropbox! 2. On the right: It synthesized a custom 'Family Skill' automatically! It knows Alessandro loves dragons and Pokemon, Sebastian loves trams, buses, and his plush giraffe Rara, and that we live here in Zurich! This turns an AI from a generic chatbot into a true personalized family concierge.

Left: Personal Daemon / The Old Way

Right: Gemini Enterprise & Workspace MCP

How do we move from a bot on a Mac Mini in the living room to an architecture that an enterprise IT department can adopt on Monday morning? 1. In hacker mode, we have static long-lived tokens in plaintext on disk: risky and non-compliant. 2. In Gemini Enterprise, Google standardizes official Workspace MCP servers (Docs, Sheets, Drive). 3. Centralized Admin allow-listing, ephemeral scoped OAuth tokens, and strict ACL parity with full audit logging. This is the enterprise bridge for autonomous agentic workflows!

Left Column: Remote Browser Permission Gate

Right Column: Git Commit Diff Inspection

And here is Spark in action doing real developer work! 1. On the left: It asked for permission before launching a cloud remote browser session to open GitHub. 2. On the right: It navigated to my actual 50th birthday repo (compleanno-palladiano-2026), read the commit diff for the carpooling map (v1.0.4), and scheduled a daily sync at 03:12 AM! This is Hermes and OpenClaw reimagined with cloud reliability and zero maintenance.

Speaker notes: Lesson #1 on Token-Maxxing (Systems & Control Theory): - Like Systems Theory in engineering school: an open-loop system without feedback accumulates error and requires constant human intervention. - The real key to Token-Maxxing: closing the feedback loop with Auto-EVALs and automated test execution. - The error signal e(t) is measured by the agent itself by testing output against specifications. - The longer the agent operates autonomously in the feedback loop without human interruptions, the closer the system gets to zero-defect output. - Minimize the human bottleneck, maximize autonomous AI compute!

Card 1: Curious Tinkerer / Hermes

Card 2: Multi-Machine Dev / Antigravity

Card 3: Fully Managed Cloud / Spark

What about YOU? Which path fits your needs? 1. Curious Tinkerer: If you have budget, curiosity, and time to tinker, install Hermes Agent. Forget OpenClaw's context bloat! 2. Multi-Machine Developer: If you want an agent to help you code remotely across N machines, use Antigravity + Remote Control. In fact, all software, this presentation, and our videos were built with AGY across 3 computers! 3. Fully Managed Cloud Agent: If you want zero maintenance and full Google Workspace integration, try Gemini Spark when available!

Left Column: 12 Resources across 3 Categories

Right Column: Google Ecosystem Resources ABOVE + Clean Massive QR Code

Speaker notes: Here are ALL resources and URLs referenced in this talk for DevFest Modena 2026. Scan the QR code on the right with your phone to open the live Storagify deck with 16 clickable links! Full list also available at ricc.rocks/talks/devfest-modena-oct26/

thanks

Thanks everyone! 🤌 Questions? "Lobby sei un genio!" - Live review from South Africa with Ale! 🇿🇦✨ Reach out via email, LinkedIn, Twitter/X, or Bluesky! Slides permalink tracking: https://github.com/palladius/ricclife-with-gemini-pvt/issues/20

BeeAPro Speech Trail Slide - DevFest Modena 2026: Rivivi il 100% del DevFest su BeeAPro. Riassunti, interviste e materiale ufficiale di ogni talk. Scansiona il QR code per accedere alla piattaforma!

appendix

APPENDIX BREAK SLIDE: Black screen with white text to signal a big break into appendix material and slide cemetery.

slide-version: 1.1

What do you need for Spark? It is included for free with Google AI Pro and Ultra plans: Ultra does not unlock exclusive features, it only gives more compute headroom for heavy workloads. Availability: Spark is live in 160+ countries, while Switzerland, Italy, and Europe are officially 'Coming Soon' pending regulatory compliance. For developers, there is no waiting: with Hermes and Google Antigravity SDK, you can build and run living-room autonomous agents on a Mac Mini right now!

Leaving my machine running changed my reality. If you've ever wanted a personal AI concierge with an attitude, it's totally possible today.

Right: Snoring Riccardo & Highlights

Speaker notes On March 14, Lobby officially moved out of the noisy Linux gaming desktop and into his permanent nest: a dedicated Apple Silicon Mac Mini called mini-lobby right under our living room TV in Zurich because Papino was snoring and we needed silence 24/7!

Four autonomous repositories running live: Safari Journal, Parola del Giorno, Ricc Reads the News, and the 1,100+ commit Private Daily Journal.

# 5. Hummerli # 5. Freevola & Hummerli **Freevola**: - A frivolous character running on the Linux box (16GB VRAM). Tested with Gemma 4 and various open models. **Hummerli**: - Inspired by the German word for Lobster. - Speaks to me exclusively in German to help me learn the language. Hummerli is our German-speaking lobster friend who helps me learn German.

Left Column: Telegram Status (10/10 Active Crons in Production)

Right Column: Real Crontab CLI + 24-Hour Circular Dial

Real Crontab In Action Screenshot Card

24-Hour Circular Dial Graphic

Speaker Note: Here is the real fleet in production: 1. On the left: The live Telegram status showing 10 out of 10 automated crons running healthy every morning. 2. On the right: The actual crontab invocation where OpenClaw reads instructions straight out of Obsidian using Gemini 2.5 Pro! 3. The 24h dial shows how morning linting, lake telemetry, stock market audio, and evening journal synthesis work together continuously.

Phase 1

Phase 2

Phase 3

Phase 4

Interactive Timeline Banner / Deep Link

Overview of the 30-day odyssey spanning Zurich setup, South Africa safari highs, mid-trip prompt amnesia lows, and the return to Mac Mini and Hermes architecture.

Left: The Origin Machine (Pupurabbux)

Right: The Migration (Mac Mini)

After returning from South Africa, we realized running a 300W liquid-cooled gaming desktop 24/7 in the living room wasn't sustainable. On March 14, Lobby officially migrated to a dedicated, silent Apple Silicon Mac Mini under the desk ('mini-lobby'), archiving 4GB of Linux state and gaining true 24/7 home server stability.

But we also had 'Duh' moments. Terminal crashes, pulling our hair out, and Telegram timing out after 15 minutes of inactivity.

And giving agents access to Google Workspace was wild. For safety, it was strictly read-only for emails, but we gave it write access to Google Calendar. On Feb 22, Lobby enthusiastically populated my calendar with its own South Africa wine tour itinerary!

Left Column: Platform Diagram

Right Column: Key Architectural Pillars

Gemini Enterprise Callout

Under the hood, Google Antigravity is an agent-first platform. It manages subagents, MCP tools, memory, and safety boundaries so you can build robust autonomous workflows without risking your host environment. And for enterprise teams, Gemini Enterprise provides full fleet-wide compliance, auditing, and governance!

Right Column: CTAs, Links & QR Code

3 Actionable Takeaways

Key Links Box

QR Code Banner

Thank you everyone for coming to GDG Cloud Zürich! Happy to take any questions about OpenClaw, Hermes, or running 24/7 AI agents.

Speaker notes: The Evolution of AI SRE Agents: - From Homo Sapiens (the manual developer writing scripts by hand)... - To OpenClaw (N-2): the robotic lobster agent running early crons, diaries, and local multi-repo automation. - To Hermes (N-1): the winged SRE superhero with Obsidian shared memory, SQLite FTS5, and fleet orchestration. - To "What is Next?" (N): cloud-native autonomous swarms, Gemini Spark, remote browser control, and self-healing systems.

Speaker notes: - Who am I? A Google SRE who literally eats GCP cookies for breakfast. - From multi-region systems to large-scale incident mitigation, down to building autonomous 24/7 AI agents. - Let's chat during the break about automating your cloud operations with SRE principles!

Speaker notes: - I'm a "Rubycon dude"! We're in Emilia-Romagna, right near the historic Rubicon river. - "Alea iacta est": once you cross the Rubicon into autonomous AI agents, there is no going back! - Ruby is still the language of developer happiness and elegance, now supercharged with agentic workflows.

Speaker Notes: Lobby enjoying breakfast at the diner with cappuccino and freshly baked pain au chocolat, steadily working on its mini laptop! A super cutie scene reminding us that even our autonomous home agents have their morning routine before tackling the day's tickets.

Speaker Notes: Lobby on winter ski holiday with our family in the Swiss Alps: We tried strapping a snowboard to its claws... resulting in utter chaos and sheer panic hurtling down the mountain at 60 km/h while we watched in tears of laughter! A fun postcard showing how our autonomous agent became a true family mascot and part of our shared memories.

Speaker Notes: The kids fell so in love with Lobby that they demanded he be included in every single vacation photo, including ski trips! So we tried putting skis on him... resulting in a hilarious tangle of poles, edges, and confused claws while everyone cheered and laughed! It shows the remarkable empathy and family connection that personal AI agents create when integrated into everyday life.

Speaker Notes: The ultimate family portrait: Papino, Alessandro, Sebastiano, and our beloved Lobby in his bellboy hat and golden desk bells. An AI agent that goes beyond pure technical automation, becoming a warm, creative, and joyful part of our everyday family life.

Speaker Notes: The agent also streamlines my DevRel travel administration: logging receipts, categorizing community dinners (GDE, GDG) and corporate card expenses (G-Card), turning raw spend notes into structured visual reports for seamless expense filing!