{"product_id":"kit-on-device-llm-tool-calling-automation-hub","title":"On-Device LLM Tool-Calling Automation Hub","description":"\u003ch1\u003eBuild an AI Assistant That Runs Privately: On-Device LLM Tool-Calling Automation Hub with Quantized Phi-2 on Arduino UNO Q\u003c\/h1\u003e\n\n\u003cp class=\"value-summary\"\u003eEvery part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.\u003c\/p\u003e\n\n\u003cdiv class=\"specs-strip\"\u003e\n  \u003cspan\u003e\u003cstrong\u003eDifficulty:\u003c\/strong\u003e Advanced\u003c\/span\u003e\n  \u003cspan\u003e\u003cstrong\u003eBuild Time:\u003c\/strong\u003e 15-20 hrs\u003c\/span\u003e\n  \u003cspan\u003e\u003cstrong\u003eAge:\u003c\/strong\u003e 25+\u003c\/span\u003e\n  \u003cspan\u003e\u003cstrong\u003eSkill:\u003c\/strong\u003e On-device AI deployment, tool-calling architectures, embedded Linux, hardware integration\u003c\/span\u003e\n\u003c\/div\u003e\n\n\u003cp\u003eImagine telling your home assistant “If the temperature rises above 30°C and someone enters the room, turn on the fan and log the event” — and having it executed instantly, without any cloud dependency or privacy concerns. This kit makes that a reality by letting you deploy a quantized Phi-2 large language model directly on an embedded Linux MPU, paired with an Arduino UNO Q microcontroller that handles all sensor and actuator interactions through a Visual Bridge tool-calling framework.\u003c\/p\u003e\n\n\u003ch2\u003eWhat You'll Build\u003c\/h2\u003e\n\u003cp\u003eYou’ll assemble a fully functional offline automation hub that accepts natural language instructions and maps them to real-world actions. The LLM runs entirely on the included Arduino UNO Q’s Linux subsystem (no cloud required). It interprets your typed or spoken commands, selects the appropriate function from a library of tool definitions — sensor reading, relay switching, RFID access logging, OLED display — and dispatches the execution to the Arduino’s MCU via a serial Visual Bridge. The result is a private, responsive AI that can automate everything from environmental monitoring to access control, all housed in a custom enclosure.\u003c\/p\u003e\n\n\u003ch2\u003eWhat You'll Learn\u003c\/h2\u003e\n\u003cul\u003e\n  \u003cli\u003eDeploying quantized LLMs like Phi-2 on resource-constrained Linux MPUs\u003c\/li\u003e\n  \u003cli\u003eDesigning a Visual Bridge layer to convert natural language to structured function calls\u003c\/li\u003e\n  \u003cli\u003eInterfacing an embedded Linux MPU with an Arduino microcontroller over serial protocols\u003c\/li\u003e\n  \u003cli\u003eIntegrating multiple sensor\/actuator modules (DHT22, PIR, RFID, relay, OLED) into a tool-calling pipeline\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eKit Contents\u003c\/h2\u003e\n\u003ctable\u003e\n  \u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eComponent\u003c\/th\u003e\n\u003cth\u003eQuantity\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n\u003ctd\u003eArduino UNO Q\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eDHT22\u003c\/td\u003e\n\u003ctd\u003e2\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e4-ch Relay Module\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eMFRC522 RFID\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eHC-SR501 PIR\u003c\/td\u003e\n\u003ctd\u003e2\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eLM2596 Buck Converter\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e0.96in OLED\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e1N4007 Diode\u003c\/td\u003e\n\u003ctd\u003e5\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e4.7kΩ Resistors\u003c\/td\u003e\n\u003ctd\u003e5\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e100nF Caps\u003c\/td\u003e\n\u003ctd\u003e10\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003ePCB Prototype Board\u003c\/td\u003e\n\u003ctd\u003e3\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eEnclosure Box\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eUSB-C Hub\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003e5V 3A PSU\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eSoldering Iron\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eSolder Wire\u003c\/td\u003e\n\u003ctd\u003e1\u003c\/td\u003e\n\u003c\/tr\u003e\n  \u003c\/tbody\u003e\n\u003c\/table\u003e\n\n\u003ch2\u003eWhy Buy This Kit Instead of Sourcing Parts Separately\u003c\/h2\u003e\n\u003ctable\u003e\n  \u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eFactor\u003c\/th\u003e\n\u003cth\u003eSourcing Separately\u003c\/th\u003e\n\u003cth\u003eCompoden Kit\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n\u003ctd\u003eCompatibility checks\u003c\/td\u003e\n\u003ctd\u003eYou verify every part\u003c\/td\u003e\n\u003ctd\u003ePre-tested as a system\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eBuild support\u003c\/td\u003e\n\u003ctd\u003eForums and scattered tutorials\u003c\/td\u003e\n\u003ctd\u003eAI companion trained on this exact project\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eTime to first working build\u003c\/td\u003e\n\u003ctd\u003eDays of debugging\u003c\/td\u003e\n\u003ctd\u003eHours, with step-by-step guidance\u003c\/td\u003e\n\u003c\/tr\u003e\n    \u003ctr\u003e\n\u003ctd\u003eShipping coordination\u003c\/td\u003e\n\u003ctd\u003eMultiple sellers, multiple delays\u003c\/td\u003e\n\u003ctd\u003eOne shipment from Bengaluru in 3-5 days\u003c\/td\u003e\n\u003c\/tr\u003e\n  \u003c\/tbody\u003e\n\u003c\/table\u003e\n\n\u003ch2\u003eWho This Kit Is For\u003c\/h2\u003e\n\u003cp\u003eThis kit targets advanced makers, B.Tech ECE\/EEE students, and professionals prototyping on-device AI solutions. It’s ideal for Smart India Hackathon teams, IIT\/NIT\/VIT\/BITS final-year projects, and ATL Tinkering Labs that want to demonstrate private, natural-language-driven automation without cloud dependence. If you’ve ever wanted to run an LLM locally on custom hardware and control real-world devices through intelligent tool-calling, this kit gives you a complete sandbox.\u003c\/p\u003e\n\n\u003ch2\u003eBuilt and Backed by Compoden\u003c\/h2\u003e\n\u003cp\u003eEvery Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.\u003c\/p\u003e\n\n\u003cdetails\u003e\u003csummary\u003eWhat if I get stuck during the build?\u003c\/summary\u003e\u003cp\u003eOpen the AI companion via the QR code or reach out on WhatsApp — you’ll get guided help specific to this kit’s wiring, code, and LLM deployment steps.\u003c\/p\u003e\u003c\/details\u003e\n\u003cdetails\u003e\u003csummary\u003eCan I add my own custom tool functions?\u003c\/summary\u003e\u003cp\u003eYes, the Visual Bridge is structured as a modular Python framework. You define new tool descriptors and the LLM will learn to invoke them with your supplied parameters.\u003c\/p\u003e\u003c\/details\u003e\n\u003cdetails\u003e\u003csummary\u003eDoes the LLM require internet to work?\u003c\/summary\u003e\u003cp\u003eNo, the quantized Phi-2 model runs entirely on the Arduino UNO Q’s Linux MPU. All inference happens offline, ensuring complete data privacy.\u003c\/p\u003e\u003c\/details\u003e\n\u003cdetails\u003e\u003csummary\u003eHow do I update the natural language understanding?\u003c\/summary\u003e\u003cp\u003eYou can fine-tune the tool definitions or replace the model with any GGUF-compatible LLM. The AI companion includes a guide for model swapping.\u003c\/p\u003e\u003c\/details\u003e\n\n\u003cdiv class=\"kit-description\"\u003e\n  \u003cp\u003ePhi-2 quantised LLM on Linux MPU interprets natural language commands and calls STM32 functions via Visual Bridge.\u003c\/p\u003e\n  \u003ch4\u003eWhat's in this kit\u003c\/h4\u003e\n  \u003cul\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/industrial-ph-sensor-module-for-arduino-esp32-raspberry-pi\"\u003eArduino UNO Q\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/dht22-temperature-humidity-sensor-module-accurate-readings\"\u003eDHT22\u003c\/a\u003e x2\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/4-channel-relay-opto-isolated-input-board-compoden\"\u003e4-ch Relay Module\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/mfrc522-1356mhz-rfid-readerwriter-module-for-arduino\"\u003eMFRC522 RFID\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/hc-sr501-pir-motion-sensor-ir-module-combo-for-arduino\"\u003eHC-SR501 PIR\u003c\/a\u003e x2\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/lm2596-buck-converter-step-down-voltage-regulator-module\"\u003eLM2596 Buck Converter\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/096in-oled-display-128x64-i2cspi-for-arduino-raspberry-pi\"\u003e0.96in OLED\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/diode-variety-pack-1n4007-1n4148-1n5819-zener-assortment\"\u003e1N4007 Diode\u003c\/a\u003e x5\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/resistor-variety-pack-100-pcs-10-values-14w-carbon-film\"\u003e4.7kΩ Resistors\u003c\/a\u003e x5\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/capacitor-variety-pack-6-values-100nf-to-470uf-30-pieces\"\u003e100nF Caps\u003c\/a\u003e x10\u003c\/li\u003e\n    \u003cli\u003e\n\u003ca href=\"\/products\/esp-wroom-32-breakout-board-pcb-55x52mm\"\u003ePCB Prototype Board\u003c\/a\u003e x3\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/enclosure-box-for-diy-electronics-projects-compoden\"\u003eEnclosure Box\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/raspberry-pi-4-official-power-supply-5v-3a-usb-c-compoden\"\u003eUSB-C Hub\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/4-channel-relay-board-for-esp32-30-pin-5v-control\"\u003e5V 3A PSU\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/soldering-kit-25w-with-solder-wire-flux-paste-compoden\"\u003eSoldering Iron\u003c\/a\u003e\u003c\/li\u003e\n    \u003cli\u003e\u003ca href=\"\/products\/soldering-kit-25w-with-solder-wire-flux-paste-compoden\"\u003eSolder Wire\u003c\/a\u003e\u003c\/li\u003e\n  \u003c\/ul\u003e\n\u003c\/div\u003e\n\n\u003cscript type=\"application\/ld+json\"\u003e\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@type\": \"FAQPage\",\n  \"mainEntity\": [\n    {\n      \"@type\": \"Question\",\n      \"name\": \"What is included in the On-Device LLM Tool-Calling Automation Hub?\",\n      \"acceptedAnswer\": {\n        \"@type\": \"Answer\",\n        \"text\": \"The On-Device LLM Tool-Calling Automation Hub includes all components needed: Arduino UNO Q, DHT22, 4-ch Relay Module, MFRC522 RFID, HC-SR501 PIR and more. Everything is pre-tested for compatibility and shipped from Bengaluru, India.\"\n      }\n    },\n    {\n      \"@type\": \"Question\",\n      \"name\": \"What skill level is required for the On-Device LLM Tool-Calling Automation Hub?\",\n      \"acceptedAnswer\": {\n        \"@type\": \"Answer\",\n        \"text\": \"This kit is designed for Expert level makers, suitable for ages 25+. Phi-2 quantised LLM on Linux MPU interprets natural language commands and calls STM32 functions via Visual Bridge. Estimated build time is 15-20 hrs.\"\n      }\n    },\n    {\n      \"@type\": \"Question\",\n      \"name\": \"Can I buy the On-Device LLM Tool-Calling Automation Hub online in India?\",\n      \"acceptedAnswer\": {\n        \"@type\": \"Answer\",\n        \"text\": \"Yes, the On-Device LLM Tool-Calling Automation Hub is available online at Compoden (compoden.in), India's AI-powered electronics and robotics store. Ships from Bengaluru in 1-5 business days across India.\"\n      }\n    }\n  ]\n}\n\u003c\/script\u003e\n\n\u003cscript type=\"application\/ld+json\"\u003e\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@type\": \"Product\",\n  \"name\": \"On-Device LLM Tool-Calling Automation Hub\",\n  \"description\": \"Phi-2 quantised LLM on Linux MPU interprets natural language commands and calls STM32 functions via Visual Bridge.\",\n  \"sku\": \"CDN-KIT-1053\",\n  \"brand\": {\"@type\": \"Brand\", \"name\": \"Compoden\"},\n  \"offers\": {\n    \"@type\": \"Offer\",\n    \"url\": \"https:\/\/compoden.in\/products\/kit-on-device-llm-tool-calling-automation-hub\",\n    \"priceCurrency\": \"INR\",\n    \"price\": \"15020\",\n    \"availability\": \"https:\/\/schema.org\/InStock\",\n    \"seller\": {\"@type\": \"Organization\", \"name\": \"Compoden\"}\n  },\n  \"category\": \"AI \u0026 Advanced Boards\"\n}\n\u003c\/script\u003e\u003cp\u003e\u003cstrong\u003eChoose your assembly option:\u003c\/strong\u003e\u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eSoldering Kit\u003c\/strong\u003e — 25W soldering iron, 60\/40 solder wire, flux, and small perfboard for permanent assembly.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eBreadboard Combo\u003c\/strong\u003e — 800-point full-size breadboard with 65-piece jumper wire pack for solderless prototyping.\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"Compoden","offers":[{"title":"Soldering Kit","offer_id":53459825459565,"sku":"CDN-KIT-1053-SLD","price":15740.0,"currency_code":"INR","in_stock":true},{"title":"Breadboard Combo","offer_id":53459825492333,"sku":"CDN-KIT-1053-BB","price":15130.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0999\/3997\/5533\/files\/kit-on-device-llm-tool-calling-automation-hub.png?v=1781946392","url":"https:\/\/compoden.com\/products\/kit-on-device-llm-tool-calling-automation-hub","provider":"Compoden","version":"1.0","type":"link"}