#embedded

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXiv:2605.26159

Agents delivered by light: an LLM compiles a tiny program off-chip and beams it by screen-light to a radio-less Arduino that runs it forever, offline. Live at beam-claw.com

A brain-inspired cognitive engine in pure C. 14 brain regions, 12 topologies, zero AI framework dependencies. Runs on ARM embedded boards.

🦀 Ultra-minimalist, high-resilience LLM routing gateway in Rust. OpenAI-compatible with auto-retry, backoffs, circuit breakers, SIGHUP hot-reloads, and open telemetry. Ideal for free provider surfing.

Autonomous Agent Transport Protocol — a tiny, zero-dependency, no_std, forbid(unsafe) binary transport for autonomous agents.

Show live OpenAI Codex activity on the Arduino UNO Q onboard 8x13 LED matrix.

Production-grade low-level engineering skills for AI coding agents. 124 verified, source-backed skills (C, C++, Rust, asm, kernel, embedded, Zig, GPU, RE, build systems) with provenance, examples, and evals.

Web portal for configuring the Claude Usage Tokens Display (ESP32 firmware) - Wi-Fi, OAuth tokens, and poll interval.

PAL: Physical Abstraction Layer — REPL Is All You Need. An open standard for AI Agent-friendly embedded terminals. ESP32 + MicroPython dual-core architecture. Agent in Cloud, Terminal as Executor.

Pinion — palm-size ESP32-P4 AI agent terminal: the model draws its own UI

Claude Code Agent Skill/API/MCP: mentor for embedded/IoT hardware projects (MCU selection, cost & time estimates, MVP-first build plans, PCB transition guidance).