Skip to content

Instantly share code, notes, and snippets.

View danilo1105's full-sized avatar
😁

Danilo F danilo1105

😁
  • Vertical 9
  • São Paulo
  • 08:21 (UTC -03:00)
View GitHub Profile
@andrisgauracs
andrisgauracs / run_prompt.sh
Created July 31, 2026 02:57
Test a custom prompt against an already-trained, already-flashed ESP32-S3 model
#!/usr/bin/env bash
# esp32-ai: test a custom prompt against an already-trained, already-flashed model.
# Does NOT retrain and does NOT rewrite the 15MB model partition.
#
# Usage:
# ./run_custom_prompt.sh "Once there was a robot"
set -euo pipefail
if [ "$#" -lt 1 ]; then
echo "Usage: $0 \"Your custom prompt\""
@andrisgauracs
andrisgauracs / build_and_flash.sh
Created July 31, 2026 02:21
One Shot Build Script For Running 28M AI Model On ESP32-S3
#!/usr/bin/env bash
# esp32-ai: clone, train, export, build, and flash — end to end
# Reproduces github.com/slvDev/esp32-ai from a bare board.
# Requires: ESP32-S3 N16R8 (16MB flash, 8MB PSRAM).
#
# Usage:
# ./build_and_flash.sh # full run: data prep, train, export, build, flash
# ./build_and_flash.sh --skip-train # reuse an existing firmware/model/model.bin, just build + flash
set -euo pipefail

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.