adafruit industries
@adafruit • 241,032 subscribers
Brooklyn, NY USA - Manufacturer, open-source hardware, certified Minority and Woman-owned Business Enterprise (M/WBE) X account managed by @ladyada & @ptorrone
Shorts
Videos
OpenClaw vs. a 475-page datasheet: let the robot do the transcribing 🦞🤖 The u-blox SAM-M8Q has been sitting on my bench for months. This little GPS module has a built-in antenna, coin cell backup, speaks both NMEA and UBX binary protocol over UART or I2C. So why isn't it in the shop already? Well, it's mostly cause of the 475-page interfacing datasheet documenting every command, struct, and config register. Hundreds of message types. I got partway through by hand with some Claude Code Sonnet assistance, but ran out of time - plus it was still tedious when babysitting Sonnet. However, now we're living in an Opus + Codex era! So I pointed my Raspberry Pi OpenClaw at it. Here's the setup: Raspberry Pi 5 running OpenClaw, wired to a QT Py RP2040, which talks to the SAM-M8Q. Opus 4.6 reads the datasheet (converted to markdown first by Sonnet 4.6 with 1M context to minimize re-parsing that PDF every session) and builds the implementation plan. I review the plan to make sure it prioritizes the most common commands and reports, and flagged some unessential sections like automotive-assist or RTK-specific. Then Codex is assigned each message implementation task as a sub-agent and writes the actual C code for the Arduino library. Opus suggested using struct-based parsing rather than digging through each uint8_t array; we just memcpy the checksummed message raw bytes onto the matching struct and extract the typed bit fields. We've got four message types done so far. After each message is implemented, Codex also writes a test sketch that will exercise / pretty-print the results of each message, great for self-testing as well as regression testing later. Tonight I'm telling it to keep going while I sleep: code, parse, test against live satellite data, fix failures, commit and push on success, then move on to the next. To me this is a great usage of "agentic" firmware development: there's no creativity in transcribing 84 different structs from a 475-page datasheet. Once the LLMs are done, I can review the PRs as if it were an everyday contributor and even make revision suggestions.
adafruit industries60,039 views • 3 months ago
Full-circle Test-driven Firmware Development with OpenClaw Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process: “Agentic test-driven firmware development.” I've used LLMs for writing code as a sort of pair-programming setup, where I dictate exactly what I want done. But this is the first time that I'm giving full access to the hardware to the LLMs and letting Claude Opus 4.5 as a manager to control Codex subagents. Not only does it parse the datasheet for the register map and functionality, Claude also comes up with a full development and test plan, writes the library, tests it on existing hardware, and then also works up a test suite that covers all of the hardware registers to make sure that the library is exercising the entire chip capability. For example, here I give it an APDS-9999 color sensor and a Neopixel ring and tell it, “hey use the Neopixel ring to verify that we're really reading red, green, and blue data properly from the sensor,” and it will do the whole thing completely autonomously… no humans involved! I still review the final code and ensure the tests genuinely validate the functionality, not just take shortcuts. There is a phenomenon known as "reward hacking" (also called "specification gaming"). The model may optimize for passing tests as a metric, rather than ensuring the code truly works as intended. So far, the results have been excellent... no surprise, since these LLMs are trained on Adafruit open-source GitHub repositories!"
adafruit industries25,105 views • 3 months ago
Updating organization at the Adabench for the New Year This coming year, we wanted to update our storage and organization: with about 700 original designs, a couple dozen in progress, and thousands of items in the shop, it's hard to keep track of all the components and devboards we need to test various combinations. Historically, we've used double-sided totes ( which are good, but the double-sidedness is a bit annoying, or the little divider boxes for small breakouts ( and snap-top boxes for SMT components ( But all these cases were sort of swimming around, and it was getting unwieldy. We're going to try to use the large IKEA ALEX drawers ( - we like them cause they're wide and thin - and maybe use something like gridfinity ( to make a flat storage surface so we can quickly find any PCB or part we need.
adafruit industries15,906 views • 1 year ago
Solenoids go clicky-clacky 🔩🔊🤖 We're testing out an I2C-to-solenoid driver today. It uses an MCP23017 expander. We like this particular chip for this usage because it has push-pull outputs, making it ideal for driving our N-channel FETs and flyback diodes. The A port connects to the 8 drivers, while the B port remains available for other GPIO purposes. For this demo, whenever we 'touch' a pin on port B to ground, the corresponding solenoid triggers provide an easy way to check speed and power usage.
adafruit industries10,437 views • 1 year ago
RP2040 LoRa Feather Tester Brains Upgrade Most of our testers use pretty simple gpio toggling to verify everything's connected - but for our Radio Feathers we want to also verify that the radio signal is connected through properly. so we use a separate radio to ping pong a message and check the RSSI. traditionally we did this with separate radio feathers but that got a little annoying to manage since they'd get lost or the battery would be dead just as we were about to get on with some testing. since our new fancy Tester Brains got an upgrade from teensy to pico, we also revised to add an EYE-SPI connector which brings plenty of GPIO and SPI over. now we have the second RFM module connected to the tester itself so it's all-in-one. a lot easier to manage!
adafruit industries11,445 views • 3 years ago
We test a tester for the Adafruit OV5640 camera breakout - Parallel-data camera breakouts are common, but we wanted to design a better one for video and image hacking. Details like i2c pullups, built-in 24mhz oscillator, auto-focus motor power supply, and heatsinking power plane!
adafruit industries11,688 views • 3 years ago
No more content to load