Local-first AI + ESP32 tools

Small, hackable, dependency-free building blocks — readable in one sitting.

Local AI · Python · Ollama

sqlite-memory
persistent long-term memory for local LLMs — one file, no vector DB
sqlite-rag
minimal RAG: embeddings + cosine in SQLite, stdlib only
ollama-doctor
find out why Ollama is slow (CPU offload / VRAM)
local-voice-edge
ESP32 voice assistant + local STT→LLM→TTS server

ESP32 · Displays · LVGL

axs15231b-landscape-lvgl
3.5" AXS15231B QSPI panel in landscape with LVGL
guition-esp32p4-lvgl9
Guition 7" ESP32-P4 + LVGL 9 baseline (+ build fixes)

3D printing

orcaslicer-cli-cookbook
OrcaSlicer from the command line + undocumented fixes

What is this

A one-person workshop building an ecosystem where local AI meets real hardware: private, offline-first assistants running on cheap boards, plus the sensors and enclosures around them. These open-source pieces are the building blocks — free, MIT, and extracted straight from the real thing.

Support the work

If any of these saved you time, the best free help is a ⭐ on the repos. If you'd like to back the project directly:

💛 Support the project ⭐ Star the repos

Follow

YouTube Instagram TikTok X Telegram