A self-hosted, compounding-memory AI assistant running on a Raspberry Pi.

NanoClaw is a personal AI assistant built on Anthropic's Claude that runs entirely on a Raspberry Pi. It connects to messaging channels (WhatsApp, Telegram, Slack, Discord), processes voice and images, schedules recurring tasks, and — unlike a standard chatbot — accumulates knowledge over time through a structured memory system.

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.

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.

Lecture 1: Introduction to Research — [📝Lecture Notebooks] [▶️Video]
Lecture 2: Introduction to Python — [📝Lecture Notebooks] [▶️Video]
Lecture 3: Introduction to NumPy — [📝Lecture Notebooks] [▶️Video]
Lecture 4: Introduction to pandas — [📝Lecture Notebooks] [▶️Video]
Lecture 5: Plotting Data — [📝Lecture Notebooks] [[▶️Vide

I’ve compiled all the resources that helped me in my GATE preparation, and I hope they help you too! 🚀

OpenAI's blog post: https://openai.com/index/introducing-openai-privacy-filter/

A local UserPromptSubmit hook for Claude Code that scans each prompt for PII with the int8 openai/privacy-filter ONNX model before the prompt is sent.

If PII is detected, the hook blocks submission and prints the detected spans. If the local detector is unavailable, the hook fails open and does not block the prompt. Blocked responses include the detected spans and OPF processing time.

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

With its built-in Bluetooth capabilities, the ESP32 can act as a Bluetooth keyboard. The below code is a minimal example of how to achieve it. It will generate the key strokes for a message whenever a button attached to the ESP32 is pressed.

For the example setup, a momentary button should be connected to pin 2 and to ground. Pin 2 will be configured as an input with pull-up.

In order to receive the message, add the ESP32 as a Bluetooth keyboard of your computer or mobile phone:

1. Go to your computers/phones settings
2. Ensure Bluetooth is turned on