Launches, releases, funding and papers about agents doing hardware work.
Newest first, as we log them.
8 d ago
CNX Software reported on 21 October that Espressif sells ESP-Mosaico, a modular ESP32-S31 kit with a square touchscreen, for $59 on its own store. Espressif's Vibe Coding guide has a coding agent such as Codex build apps from the esp-mosaico-vibe workspace and install them over USB. An on-board agent, ESP-Claw, answers chat requests.
21 d ago
In September Nordic Semiconductor added skills to its Nordic MCP server that drive a Power Profiler Kit II and SEGGER J-Link probes. The PPK2 skill captures long measurement runs and flags anomalies against a reference pattern; the debug skill runs GDB sessions. The nRF Connect extension for VS Code now shares build context. The post shows no runs.
21 d ago
Jorge García-Carrasco and colleagues published a benchmark in the Journal of Systems Architecture that scores LLM coding agents on 5 embedded-control tasks. Agents must build firmware, verify it and iterate under 4 feedback levels, from one-shot to oracle-style hints. The paper reports 420 runs on simulated ESP32 firmware: GPT-5.4 passed most often, and Qwen3.5-27B was the strongest local model.
22 d ago
Silicon Labs opened a public beta of its Simplicity AI SDK on 22 September, connecting AI coding assistants to its SDKs, tools and hardware. RFID Journal reports that GitHub Copilot and Codex are validated and that support starts with Bluetooth LE. A Hardware Intent Agent that drafts projects from board schematics is due in alpha in January 2027.
49 d ago
SEGGER and Embedder announced on 10 September that Embedder's firmware agent can now drive J-Link and J-Trace debug probes. The announcement says the agent loads builds, sets breakpoints, reads registers and memory and watches RTT output, then keeps debugging on the target until the code works. It gives no availability date or price.
2 mo ago
Daniel Frassinelli of Veecle reviewed first-party hardware MCP servers and found that seven chip and tooling vendors shipped them between October 2025 and August 2026. He found no official server from ST, Infineon or Renesas. He writes that none of the vendor servers runs firmware without a physical board; Veecle's own product, Chiplab, targets that gap.
3 mo ago
FWAuto's 3.6-minute video runs its own firmware agent through an STM32 edge-AI job on an STM32F4DISCOVERY board. The agent checks the toolchain, integrates an existing NanoEdge AI library, and builds and flashes over ST-LINK. From 02:52 it verifies gestures on the board and writes an evidence report. Model training is outside the demo's scope.
4 mo ago
Zhihan Zhang and colleagues, mostly at the University of Washington, published Embedded Arena, a benchmark that scores agents' model and firmware edits on microcontrollers. Boards include a MAX78000, an ESP32-S3 and an STM32N6. The paper reports Claude Opus 4.7 and Gemini 3.1 Pro failing every deployment without hardware feedback; with it, the first success came within 3 iterations.
4 mo ago
H2Loop launched Hydron on Hacker News, an embedded coding agent for VS Code and the terminal that answers from pre-indexed datasheets. The launch post lists more than 580 indexed platforms and peripherals, including STM32, ESP32 and RP2040 parts. An agentic serial monitor shipped at launch; GDB integration and a log reader were promised within 2 weeks.
5 mo ago
Memfault released an MCP server with 12 read-only tools covering devices, issues, metrics and software versions. In the launch post, Claude Code finds the day's worst new crash, matches its stack trace to the checked-out firmware and drafts a fix. A GitHub MCP server opens the pull request. Memfault says the tools cannot change devices or trigger OTA updates.
5 mo ago
Nordic Semiconductor released 2 MCP servers that connect coding assistants such as Claude Code to its SDK and cloud. The Nordic MCP server adds documentation search, an nrfutil reference, a UART monitor script and SDK workflow commands. The nRF Cloud server reads fleet data such as logs and coredumps, without write access. The post shows no hardware runs.
5 mo ago
Penglin Dai and co-authors describe AutoMCU, an LLM multi-agent system that designs neural networks to fit a microcontroller's RAM and flash limits. Vendor toolchain checks reject candidates that would not fit before any training. The paper reports competitive CIFAR accuracy after 1 to 2 hours of customization and tests on several STM32 parts; no code is linked.
5 mo ago
Craig Schindler, CTO of Assemble Labs, describes how the company has AI agents write experiments for embedded devices and interpret sensor and power data. The 10-minute interview was recorded at NVIDIA GTC 2026. His main case study is a wearable health sensor, including how power regressions are found and fixed. The video shows no bench footage of the agents.
5 mo ago
Espressif published a recap on 14 May of ESP32 projects from Anthropic's Code with Claude event, where each attendee got an ESP32-S3 M5Stack Cardputer. Attendees described a program in plain language, and Claude Code wrote and flashed it. The post also covers Claude Desktop Buddy, a BLE reference design on the M5StickC Plus, and Espressif's own ESP Desktop Buddy library.
5 mo ago
Root Access, a US maker of electronics for drones and robots, opened its Seb coding agent to the public on 8 May. In a Show HN post, founding engineer Vignesh K, a former TI applications engineer, says Seb reads schematics, datasheets and BOMs, mixes deterministic algorithms with LLM calls and connects to debuggers and logs. We saw no demo.
14 mo ago
Embedder launched its firmware coding agent on Hacker News on 15 August 2025 with a demo adding a magnetometer to a Pebble 2 Duo. Founders Bob Wei and Ethan Gibbs said it reads uploaded datasheets and schematics, checks output over a serial console and steps through code with GDB. SEGGER announced J-Link and J-Trace probe access in September 2026.
15 mo ago
BootLoop, a Y Combinator Summer 2025 startup founded by Noah Pacik-Nelson and Chris Markus, is building an AI agent that writes and tests firmware. The company says the agent reads datasheets and schematics, then validates code on customer boards with oscilloscopes, logic analyzers and debug probes. In pilots, its own engineers run the agent and a person reviews every line.
