An ESP32 dashboard built three ways: Habr author compares Claude Code, Codex and Antigravity

Habr author Yadulla Abidi compared three AI coding assistants, Claude Code, Codex and Antigravity, on a real hardware project: building an information dashboard around an ESP32 microcontroller with an OLED display and a temperature sensor.

What task did the assistants get?

By 2026 there are a lot of AI coding assistants, and they behave differently depending on the type of task. A model that can knock out a flawless website in a couple of minutes can get completely stuck on a complex commercial coding project. Small hobbyist microcontroller builds, however, suit these models almost perfectly, the author observes, and this is where they can really shine.

That is why Abidi chose a simple but non-trivial task for the comparison: an ESP32 dashboard with an OLED screen and a temperature sensor that also has to run several tasks in parallel. In other words, the firmware had to work as proper multitasking firmware rather than a linear script.

How did Claude Code, Codex and Antigravity perform?

Three assistants took part in the head-to-head: Claude Code from Anthropic, Codex from OpenAI, and Antigravity. In the end, all three tools delivered a working prototype of the dashboard, meaning each handled the basic task of writing microcontroller firmware from scratch.

• Project: an ESP32 information dashboard with an OLED display and a temperature sensor
• Requirement: firmware support for several parallel tasks
• Compared: Claude Code (Anthropic), Codex (OpenAI) and Antigravity
• All three assistants succeeded and delivered a working prototype

But as the author stresses, the fact that all three models completed the task does not mean you can pick an assistant for projects like this blindly. The route to a working prototype and the quality of the final code differed noticeably between the assistants.

What this means

The comparison shows that AI coding assistants in 2026 are mature enough to handle niche hardware work, such as writing microcontroller firmware, that used to require specialist embedded developers. That maturity is uneven, though: for hobbyist electronics projects, you should still choose your tool deliberately rather than grab whichever one is closest at hand.