Real AI agent use cases, with sources and setup prompts
Devices people hacked, built or reused by pairing a coding agent with real hardware. 11 matching use cases below, each with a public source.
Looking for something else? Search all 660 use cases or .
Connect your agent to Home Assistant via MCP and route automations that need judgement through it; talk to it with an ESP32 voice device.
A maker built a physical voice interface for his own AI agent on an ESP32, powered by Hermes Agent from Nous Research, and documented the build in a 16-part thread.
Konnect is a KiCad 10 plugin that lets Claude and other assistants design schematics and PCBs over MCP: 228 tools for schematic capture, layout, routing, ERC/DRC checks, JLCPCB part search and manufacturing exports, with skills that teach Claude KiCad conventions.
Niraj Rajgor used Codex and T3 Code on his Mac to have an agent connect to his Kindle, jailbreak it with GPT-6 Astra and build KindleCTL, a slideshow app that cycles ten photos. He writes up why passing tests was not the same as working on the e-ink screen.
Vibe-coded a fridge magnet shopping list on an M5Stack e-ink device, synced with a phone web app over Wi-Fi.
Ran a 35B Qwen model on a Pi with connectors to the car's OBD port and the maker's cloud service.
The author used AI to reverse engineer the SunnyFit BLE protocol and built a small terminal connector that publishes live workout data to Redis pub/sub for any visualization.
PS5LM runs llama.cpp on the PS5's GPU and serves any GGUF model to your laptop, phone and coding tools through OpenAI- and Anthropic-style APIs. It needs no PC while it runs, no cloud and no account.
A developer in Bengaluru found Hyundai's official app ugly, reverse engineered his car key and vibe coded his own Mac app. It locks, unlocks, remote starts and sets climate on his Hyundai Creta, even through Siri.
Chiplab is an MCP platform that lets agents compile, simulate and validate firmware on the actual target chip without physical hardware, for testing, porting to a new chip or debugging a HardFault.
Reverse-engineered a Nokia 110 after Android install failed on 48MB RAM, then ran an AI agent that automates a few actions.
How to make faceless YouTube videos with AI · How to automate work with n8n and AI · How to vibe code an app with Claude Code · How to build AI agents for SEO and ads · How to run multiple coding agents together · How to build an MCP server for AI agents · How to add memory to coding agents · How to secure vibe-coded apps and agents · How to observe and debug AI agents · How to build agent memory and context layers · How to control coding agents from your phone · How to add payments to vibe-coded apps · How to run local LLMs with AI agents · How to set up Grok Bot agents for real work · How to build with Gemini 4 Argon and Gemini agents · How to use AI agents for taxes, bills and budgets · How to make AI video ads and Reels with agents · How to set up Hermes Agent workflows · How to vibe code a game with AI · How to replace SaaS subscriptions with vibe-coded tools · How to use AI agents for errands, calls and shopping · How to use Cursor agents and automations · How to make 3D scenes and models with AI and Blender · How to use Claude Code skills and plugins · How to cut AI coding agent costs and token use · How to automate a small business with AI agents · How to compare AI models on the same prompt
Five real AI use cases with setups, every morning. Free.
The Daily 5 will arrive in your inbox each morning. Unsubscribe any time.
Send the public link (post, video, repo or write-up). We credit you and link back.