home.social

#smart-home — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #smart-home, aggregated by home.social.

fetched live
  1. The 4-camera solar security bundle that works with Alexa and never needs recharging.

    ANRAN Solar Security Cameras Wireless Outdoor Built-in Solar Panel

    🔭 https://www.amazon.com/dp/B0D1TSH73Z?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ANRAN Solar Security Cameras W...

  2. Indoor/outdoor dome cameras with 80ft IR night vision. HD-TVI compatible, dirt cheap per cam.

    ZOSI 2Pack 2.0MP HD 1080P 1920TVL CCTV Dome Security Cameras

    🔭 https://www.amazon.com/dp/B08ZXXG9MR?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ZOSI 2Pack 2.0MP HD 1080P 1920...

  3. 2-pack of 1080P dome cameras with 80ft night vision for DVR systems. $46 for both 🛡️

    ZOSI 2Pack 2.0MP HD 1080P 1920TVL CCTV Dome Security Cameras

    🔭 https://www.amazon.com/dp/B08ZXXG9MR?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ZOSI 2Pack 2.0MP HD 1080P 1920...

  4. Ich habe (mit Claude) eine einfache Rückseite für die großartige Kombi-Wandhalterung für IKEA BILRESA & TIMMERFLOTTE von Dillan Stock modelliert, damit man die Halterung auch außerhalb von Australien verwenden kann: https://dmnsk.de/pvUD #3DPrint #Smarthome

  5. Ich habe (mit Claude) eine einfache Rückseite für die großartige Kombi-Wandhalterung für IKEA BILRESA & TIMMERFLOTTE von Dillan Stock modelliert, damit man die Halterung auch außerhalb von Australien verwenden kann: https://dmnsk.de/pvUD #3DPrint #Smarthome

  6. AI detection + color night vision + 2-way talk on a 5MP system with 1TB storage. Serious setup.

    5MP WiFi Home Security Camera System Outdoor

    🔭 https://www.amazon.com/dp/B0GJ5KWVR3?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    5MP WiFi Home Security Camera ...

  7. ANRAN 4-pack: battery + solar powered WiFi cameras with AI detection and Alexa support.

    ANRAN Solar Security Cameras Wireless Outdoor Built-in Solar Panel

    🔭 https://www.amazon.com/dp/B0D1TSH73Z?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ANRAN Solar Security Cameras W...

  8. Wireless 2K solar cameras with color night vision. 4 cameras, one property, zero wiring.

    ANRAN Solar Security Cameras Wireless Outdoor Built-in Solar Panel

    🔭 https://www.amazon.com/dp/B0D1TSH73Z?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ANRAN Solar Security Cameras W...

  9. Solar + battery + AI detection + color night vision — the complete wireless security setup, under $60.

    Noorio 1080P Solar Security Camera Wireless Outdoor

    🔭 https://www.amazon.com/dp/B0GBXM22H6?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    Noorio 1080P Solar Security Ca...

  10. Nachdem das #iPhone18Pro auf dem Markt ist, warten viele #Apple-Fans ungeduldig auf das faltbare #iPhoneDuo, das ja am 23. Oktober offiziell startet. Doch der Oktober könnte noch mehr bringen, denn Apple wird nachgesagt, dass es noch zahlreiche #SmartHome-Produkte in der Pipeline hat.

    Das und mehr waren unsere Highlights der Woche: appgefahren.de/?p=405995

    #appgefahren #AppleBlog #Tech #TechBlog #iPhone #iPad #Mac

  11. Nachdem das #iPhone18Pro auf dem Markt ist, warten viele #Apple-Fans ungeduldig auf das faltbare #iPhoneDuo, das ja am 23. Oktober offiziell startet. Doch der Oktober könnte noch mehr bringen, denn Apple wird nachgesagt, dass es noch zahlreiche #SmartHome-Produkte in der Pipeline hat.

    Das und mehr waren unsere Highlights der Woche: appgefahren.de/?p=405995

    #appgefahren #AppleBlog #Tech #TechBlog #iPhone #iPad #Mac

  12. Nachdem das #iPhone18Pro auf dem Markt ist, warten viele #Apple-Fans ungeduldig auf das faltbare #iPhoneDuo, das ja am 23. Oktober offiziell startet. Doch der Oktober könnte noch mehr bringen, denn Apple wird nachgesagt, dass es noch zahlreiche #SmartHome-Produkte in der Pipeline hat.

    Das und mehr waren unsere Highlights der Woche: appgefahren.de/?p=405995

    #appgefahren #AppleBlog #Tech #TechBlog #iPhone #iPad #Mac

  13. Nachdem das #iPhone18Pro auf dem Markt ist, warten viele #Apple-Fans ungeduldig auf das faltbare #iPhoneDuo, das ja am 23. Oktober offiziell startet. Doch der Oktober könnte noch mehr bringen, denn Apple wird nachgesagt, dass es noch zahlreiche #SmartHome-Produkte in der Pipeline hat.

    Das und mehr waren unsere Highlights der Woche: appgefahren.de/?p=405995

    #appgefahren #AppleBlog #Tech #TechBlog #iPhone #iPad #Mac

  14. Nachdem das auf dem Markt ist, warten viele -Fans ungeduldig auf das faltbare , das ja am 23. Oktober offiziell startet. Doch der Oktober könnte noch mehr bringen, denn Apple wird nachgesagt, dass es noch zahlreiche -Produkte in der Pipeline hat.

    Das und mehr waren unsere Highlights der Woche: appgefahren.de/?p=405995

  15. 6 vintage-style E12 LED bulbs that slash energy use while keeping cozy warm light.

    AMDTU E12 LED Candelabra Light Bulb 25W Frosted Chandelier Dimmable

    🔭 https://www.amazon.com/dp/B0BW2XK2T7?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    AMDTU E12 LED Candelabra Light...

  16. 4-pack of 2K solar security cameras with human detection and spotlight. Cover every angle ☀️

    ANRAN Solar Security Cameras Wireless Outdoor Built-in Solar Panel

    🔭 https://www.amazon.com/dp/B0D1TSH73Z?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ANRAN Solar Security Cameras W...

  17. ZOSI 2-pack: crisp 1080P, 80ft night vision, works with your existing DVR. $23 per camera.

    ZOSI 2Pack 2.0MP HD 1080P 1920TVL CCTV Dome Security Cameras

    🔭 https://www.amazon.com/dp/B08ZXXG9MR?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ZOSI 2Pack 2.0MP HD 1080P 1920...

  18. Dome security cams that see 80ft in the dark. 2-pack for under $50 — unbeatable value.

    ZOSI 2Pack 2.0MP HD 1080P 1920TVL CCTV Dome Security Cameras

    🔭 https://www.amazon.com/dp/B08ZXXG9MR?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ZOSI 2Pack 2.0MP HD 1080P 1920...

  19. 5G + 2.4G WiFi solar camera with expandable local storage. $56 and it protects your whole property.

    Noorio 1080P Solar Security Camera Wireless Outdoor

    🔭 https://www.amazon.com/dp/B0GBXM22H6?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    Noorio 1080P Solar Security Ca...

  20. 1080P solar security camera with AI human detection. No monthly fees, free local storage.

    Noorio 1080P Solar Security Camera Wireless Outdoor

    🔭 https://www.amazon.com/dp/B0GBXM22H6?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    Noorio 1080P Solar Security Ca...

  21. Wired HD dome cameras with true 80ft night vision. Add real coverage to your DVR for pennies.

    ZOSI 2Pack 2.0MP HD 1080P 1920TVL CCTV Dome Security Cameras

    🔭 https://www.amazon.com/dp/B08ZXXG9MR?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    ZOSI 2Pack 2.0MP HD 1080P 1920...

  22. The solar camera that monitors your home for months without touching a wire. AI detection built in.

    Noorio 1080P Solar Security Camera Wireless Outdoor

    🔭 https://www.amazon.com/dp/B0GBXM22H6?tag=jwebb004-20 #ad #paidlink #AmazonAffiliate #SmartHome #HomeSecurity

    Noorio 1080P Solar Security Ca...

  23. Heizung läuft, Fenster steht offen – Energie verschwendet. 🪟

    In Home Assistant eine Automation anlegen: Als Auslöser den Fensterkontakt wählen, Zustand "offen". Als Aktion den Heizkörperthermostat auf den Modus "aus" setzen. Eine zweite Automation macht das bei "geschlossen" rückgängig.

    #HomeAssistant #SmartHome

  24. Heizung läuft, Fenster steht offen – Energie verschwendet. 🪟

    In Home Assistant eine Automation anlegen: Als Auslöser den Fensterkontakt wählen, Zustand "offen". Als Aktion den Heizkörperthermostat auf den Modus "aus" setzen. Eine zweite Automation macht das bei "geschlossen" rückgängig.

    #HomeAssistant #SmartHome

  25. Heizung läuft, Fenster steht offen – Energie verschwendet. 🪟

    In Home Assistant eine Automation anlegen: Als Auslöser den Fensterkontakt wählen, Zustand "offen". Als Aktion den Heizkörperthermostat auf den Modus "aus" setzen. Eine zweite Automation macht das bei "geschlossen" rückgängig.

    #HomeAssistant #SmartHome

  26. Heizung läuft, Fenster steht offen – Energie verschwendet. 🪟

    In Home Assistant eine Automation anlegen: Als Auslöser den Fensterkontakt wählen, Zustand "offen". Als Aktion den Heizkörperthermostat auf den Modus "aus" setzen. Eine zweite Automation macht das bei "geschlossen" rückgängig.

    #HomeAssistant #SmartHome

  27. Episode 38 ist raus!

    Eine ganze Woche Messe - Home Assistant auf der IFA, Pebble und optimierte Arbeitsumgebungen

    share.transistor.fm/s/13d953bf

    #homeassistant #smarthome #homelab #ifa #pebble #dotfiles #macos #epaper #opendisplay #shelly

    Viel Spaß beim Hören wünschen euch:
    @ajfriesen und @behweh

  28. Episode 38 ist raus!

    Eine ganze Woche Messe - Home Assistant auf der IFA, Pebble und optimierte Arbeitsumgebungen

    share.transistor.fm/s/13d953bf

    #homeassistant #smarthome #homelab #ifa #pebble #dotfiles #macos #epaper #opendisplay #shelly

    Viel Spaß beim Hören wünschen euch:
    @ajfriesen und @behweh

  29. Episode 38 ist raus!

    Eine ganze Woche Messe - Home Assistant auf der IFA, Pebble und optimierte Arbeitsumgebungen

    share.transistor.fm/s/13d953bf

    #homeassistant #smarthome #homelab #ifa #pebble #dotfiles #macos #epaper #opendisplay #shelly

    Viel Spaß beim Hören wünschen euch:
    @ajfriesen und @behweh

  30. Episode 38 ist raus!

    Eine ganze Woche Messe - Home Assistant auf der IFA, Pebble und optimierte Arbeitsumgebungen

    share.transistor.fm/s/13d953bf

    #homeassistant #smarthome #homelab #ifa #pebble #dotfiles #macos #epaper #opendisplay #shelly

    Viel Spaß beim Hören wünschen euch:
    @ajfriesen und @behweh

  31. Follow-up to my Jev × Home Assistant post: two comments on the last one deserved a real answer, not just a reply.

    @oneclickclaw_io asked why not feed Jev's context to a small local model instead. Fair point - my prompts really were just snapshots (humidity *now*, flow *now*), no memory of what led there.

    @nocalla asked whether that's not exactly what the Bayesian sensor is for.

    Both got tested, not just answered:

    → Why not local: the box is an N100 mini PC, 4 cores, 16 GB RAM, no GPU, already running HA Core + recorder + Zigbee2MQTT. A local model's own numbers (from the router benchmark) put it at 1.5-3s/call on that class of hardware, several times an hour, contending with real-time Zigbee. And the actual gap was never model intelligence - Jev has a 32k-token window and was only getting ~565 tokens of *current* facts.

    → So instead: a compact-history script built on Home Assistant's own recorder statistics, a 24h house timeline, per-room humidity baselines, a broken-sensor safety net (turns out two humidity sensors had been stuck at 0% - again), per-decision shadow/active switches, and a feedback loop - "who was right?" on the phone, scored on a scoreboard, summarised every week.

    → Bayesian sensor: close, but not the same tool. You hand-estimate every probability yourself, it's strictly on/off, treats correlated clues as independent, and has no idea when its own inputs are lying. Jev takes plain facts, returns a full distribution over N options, and reasons over the whole state. Bayesian still wins for signals you already understand and want fully offline (occupancy, say) - and the two combine nicely.

    Real production numbers from the first days: 267 calls, ~206k tokens, $0.0087 that day. And a live finding I didn't expect: the VMC decision disagrees with its own rule 14/14 times at low confidence, while the shutters decision agrees 78/78 times - exactly why the per-decision switch earns its keep.

    Full write-up:
    blog.mornati.net/jev-home-assi

    #HomeAssistant #SmartHome #HomeAutomation #AI #LLM #SelfHosted

  32. Follow-up to my Jev × Home Assistant post: two comments on the last one deserved a real answer, not just a reply.

    @oneclickclaw_io asked why not feed Jev's context to a small local model instead. Fair point - my prompts really were just snapshots (humidity *now*, flow *now*), no memory of what led there.

    @nocalla asked whether that's not exactly what the Bayesian sensor is for.

    Both got tested, not just answered:

    → Why not local: the box is an N100 mini PC, 4 cores, 16 GB RAM, no GPU, already running HA Core + recorder + Zigbee2MQTT. A local model's own numbers (from the router benchmark) put it at 1.5-3s/call on that class of hardware, several times an hour, contending with real-time Zigbee. And the actual gap was never model intelligence - Jev has a 32k-token window and was only getting ~565 tokens of *current* facts.

    → So instead: a compact-history script built on Home Assistant's own recorder statistics, a 24h house timeline, per-room humidity baselines, a broken-sensor safety net (turns out two humidity sensors had been stuck at 0% - again), per-decision shadow/active switches, and a feedback loop - "who was right?" on the phone, scored on a scoreboard, summarised every week.

    → Bayesian sensor: close, but not the same tool. You hand-estimate every probability yourself, it's strictly on/off, treats correlated clues as independent, and has no idea when its own inputs are lying. Jev takes plain facts, returns a full distribution over N options, and reasons over the whole state. Bayesian still wins for signals you already understand and want fully offline (occupancy, say) - and the two combine nicely.

    Real production numbers from the first days: 267 calls, ~206k tokens, $0.0087 that day. And a live finding I didn't expect: the VMC decision disagrees with its own rule 14/14 times at low confidence, while the shutters decision agrees 78/78 times - exactly why the per-decision switch earns its keep.

    Full write-up:
    blog.mornati.net/jev-home-assi

    #HomeAssistant #SmartHome #HomeAutomation #AI #LLM #SelfHosted

  33. Follow-up to my Jev × Home Assistant post: two comments on the last one deserved a real answer, not just a reply.

    @oneclickclaw_io asked why not feed Jev's context to a small local model instead. Fair point - my prompts really were just snapshots (humidity *now*, flow *now*), no memory of what led there.

    @nocalla asked whether that's not exactly what the Bayesian sensor is for.

    Both got tested, not just answered:

    → Why not local: the box is an N100 mini PC, 4 cores, 16 GB RAM, no GPU, already running HA Core + recorder + Zigbee2MQTT. A local model's own numbers (from the router benchmark) put it at 1.5-3s/call on that class of hardware, several times an hour, contending with real-time Zigbee. And the actual gap was never model intelligence - Jev has a 32k-token window and was only getting ~565 tokens of *current* facts.

    → So instead: a compact-history script built on Home Assistant's own recorder statistics, a 24h house timeline, per-room humidity baselines, a broken-sensor safety net (turns out two humidity sensors had been stuck at 0% - again), per-decision shadow/active switches, and a feedback loop - "who was right?" on the phone, scored on a scoreboard, summarised every week.

    → Bayesian sensor: close, but not the same tool. You hand-estimate every probability yourself, it's strictly on/off, treats correlated clues as independent, and has no idea when its own inputs are lying. Jev takes plain facts, returns a full distribution over N options, and reasons over the whole state. Bayesian still wins for signals you already understand and want fully offline (occupancy, say) - and the two combine nicely.

    Real production numbers from the first days: 267 calls, ~206k tokens, $0.0087 that day. And a live finding I didn't expect: the VMC decision disagrees with its own rule 14/14 times at low confidence, while the shutters decision agrees 78/78 times - exactly why the per-decision switch earns its keep.

    Full write-up:
    blog.mornati.net/jev-home-assi

    #HomeAssistant #SmartHome #HomeAutomation #AI #LLM #SelfHosted

  34. Follow-up to my Jev × Home Assistant post: two comments on the last one deserved a real answer, not just a reply.

    @oneclickclaw_io asked why not feed Jev's context to a small local model instead. Fair point - my prompts really were just snapshots (humidity *now*, flow *now*), no memory of what led there.

    @nocalla asked whether that's not exactly what the Bayesian sensor is for.

    Both got tested, not just answered:

    → Why not local: the box is an N100 mini PC, 4 cores, 16 GB RAM, no GPU, already running HA Core + recorder + Zigbee2MQTT. A local model's own numbers (from the router benchmark) put it at 1.5-3s/call on that class of hardware, several times an hour, contending with real-time Zigbee. And the actual gap was never model intelligence - Jev has a 32k-token window and was only getting ~565 tokens of *current* facts.

    → So instead: a compact-history script built on Home Assistant's own recorder statistics, a 24h house timeline, per-room humidity baselines, a broken-sensor safety net (turns out two humidity sensors had been stuck at 0% - again), per-decision shadow/active switches, and a feedback loop - "who was right?" on the phone, scored on a scoreboard, summarised every week.

    → Bayesian sensor: close, but not the same tool. You hand-estimate every probability yourself, it's strictly on/off, treats correlated clues as independent, and has no idea when its own inputs are lying. Jev takes plain facts, returns a full distribution over N options, and reasons over the whole state. Bayesian still wins for signals you already understand and want fully offline (occupancy, say) - and the two combine nicely.

    Real production numbers from the first days: 267 calls, ~206k tokens, $0.0087 that day. And a live finding I didn't expect: the VMC decision disagrees with its own rule 14/14 times at low confidence, while the shutters decision agrees 78/78 times - exactly why the per-decision switch earns its keep.

    Full write-up:
    blog.mornati.net/jev-home-assi

  35. Analoge Strommessdosen und Raumklimageräte anschaffen oder Zigbee/Matter-kompatible Geräte holen und in Home Assistant einsteigen?

    Ich möchte wissen, wie viel Strom durch welche Steckdose geht und welche Temperatur und Luftfeuchtigkeit in welchem Raum zu welcher Zeit bestehen.

    Das alles digital und vernetzt zu haben, vielleicht sogar in Grafana ein Dashboard dazu bauen zu können, klingt schon praktisch

    #smarthome #homeAssistant #internetOfThings #energiekostenmessgerät #heizen #strom #zigbee #matter

  36. Analoge Strommessdosen und Raumklimageräte anschaffen oder Zigbee/Matter-kompatible Geräte holen und in Home Assistant einsteigen?

    Ich möchte wissen, wie viel Strom durch welche Steckdose geht und welche Temperatur und Luftfeuchtigkeit in welchem Raum zu welcher Zeit bestehen.

    Das alles digital und vernetzt zu haben, vielleicht sogar in Grafana ein Dashboard dazu bauen zu können, klingt schon praktisch

    #smarthome #homeAssistant #internetOfThings #energiekostenmessgerät #heizen #strom #zigbee #matter

  37. Analoge Strommessdosen und Raumklimageräte anschaffen oder Zigbee/Matter-kompatible Geräte holen und in Home Assistant einsteigen?

    Ich möchte wissen, wie viel Strom durch welche Steckdose geht und welche Temperatur und Luftfeuchtigkeit in welchem Raum zu welcher Zeit bestehen.

    Das alles digital und vernetzt zu haben, vielleicht sogar in Grafana ein Dashboard dazu bauen zu können, klingt schon praktisch

    #smarthome #homeAssistant #internetOfThings #energiekostenmessgerät #heizen #strom #zigbee #matter

  38. Analoge Strommessdosen und Raumklimageräte anschaffen oder Zigbee/Matter-kompatible Geräte holen und in Home Assistant einsteigen?

    Ich möchte wissen, wie viel Strom durch welche Steckdose geht und welche Temperatur und Luftfeuchtigkeit in welchem Raum zu welcher Zeit bestehen.

    Das alles digital und vernetzt zu haben, vielleicht sogar in Grafana ein Dashboard dazu bauen zu können, klingt schon praktisch

    #smarthome #homeAssistant #internetOfThings #energiekostenmessgerät #heizen #strom #zigbee #matter

  39. Heating accounts for 80% of energy use in EU homes, making it our largest winter expense. Managing this cost is critical for many.

    We explain how to strategically use technology to stop waste based on your budget, covering everything from under-€30 diagnostics to smart home upgrades and dynamic tariffs.

    movetheneedle.news/brands/mtn-

    #energy #efficiency #smarthome #sustainability #Europe #EU #technology #energypoverty #innovation

  40. Heating accounts for 80% of energy use in EU homes, making it our largest winter expense. Managing this cost is critical for many.

    We explain how to strategically use technology to stop waste based on your budget, covering everything from under-€30 diagnostics to smart home upgrades and dynamic tariffs.

    movetheneedle.news/brands/mtn-

    #energy #efficiency #smarthome #sustainability #Europe #EU #technology #energypoverty #innovation

  41. Heating accounts for 80% of energy use in EU homes, making it our largest winter expense. Managing this cost is critical for many.

    We explain how to strategically use technology to stop waste based on your budget, covering everything from under-€30 diagnostics to smart home upgrades and dynamic tariffs.

    movetheneedle.news/brands/mtn-

    #energy #efficiency #smarthome #sustainability #Europe #EU #technology #energypoverty #innovation

  42. Heating accounts for 80% of energy use in EU homes, making it our largest winter expense. Managing this cost is critical for many.

    We explain how to strategically use technology to stop waste based on your budget, covering everything from under-€30 diagnostics to smart home upgrades and dynamic tariffs.

    movetheneedle.news/brands/mtn-

    #energy #efficiency #smarthome #sustainability #Europe #EU #technology #energypoverty #innovation

  43. My home automations know thresholds, not context.

    Sump pump runs 2 min after a rainy night → alert.
    Long shower → "possible leak".
    Washer pauses to soak → "finished", 20 min too early.

    So I gave the "is this normal?" question to Jev, TypeSafe's decision model. You send it a few lines of facts and a typed question, and it answers with a calibrated probability. No free text, no JSON to parse.

    How it's wired into Home Assistant:
    • The old rule always computes its answer. Jev only advises.
    • One switch: shadow (log only), active, or off.
    • An error, a spent budget or low confidence → the rule wins, so the alert still fires.
    • 6 automations: sump pump, water, temperature drops, shutters, ventilation, laundry.

    Cost: 133 calls and 75k tokens on day one, about $3 a year for the whole house.

    Two lessons that aren't about AI:
    1. Writing the facts for the model made me read them. Two humidity sensors had been stuck at 0 %, and my old rules were using them.
    2. My GitOps sync had been failing silently for 5 weeks. Merged ≠ deployed.

    Also in the post: can Laya do the same job locally, to keep occupancy data at home?

    blog.mornati.net/jev-home-assi

    #HomeAssistant #SmartHome #HomeAutomation #LLM #AI #SelfHosted