LLM

Still on improving our AI-based, embedded software workflow, this article applies the same AI-agent discipline to Zephyr. Using the same M5 stack ESP Dualkey board, specs, integration rules,plan→execute→commit→test, reusable modules, journals, and Git - without redefining the product.

AI assistants are most effective on ESP32 Rust firmware when you supply clear specs, pinned crates, reference implementations (often ESP-IDF C), and a tight verify loop. The article discusses good practices, pitfalls, discipline, and entropy. A brief explanation about the device is also included, along with the repository and all artifacts.

This article introduces how to connect your AI agent to official, up-to-date Espressif documentation directly inside your AI applications — with installation steps, example prompts, and best practices.

This article announces the Private AI Agent Platform

ESP RainMaker now supports the Model Context Protocol (MCP), enabling natural language interactions with your IoT devices via tools like Claude, Cursor, Gemini CLI, Windsurf, etc. This blog introduces the new stdio-based MCP server, outlines use cases, and hints at what’s next.