-
2026-04-05Your First Reticulum Install (Software Only, No Hardware)
Install Reticulum on any computer, connect to the public testnet, and verify connectivity — no special hardware needed. A 5-minute quickstart.
-
2026-04-05WTF is Reticulum? A Plain-English Overview
A no-jargon introduction to Reticulum — what it is, how it compares to traditional networking and Meshtastic, and why it matters for private, censorship-resistant communication.
-
2026-04-05Sideband: Encrypted Messaging on Your Phone
Set up Sideband, the Reticulum encrypted messenger for Android and desktop. No sign-ups, no servers, no metadata — just cryptographic identity and peer-to-peer messaging.
-
2026-04-05Send Your First Encrypted Message with MeshChat
Install MeshChat, the browser-based Reticulum messaging client, and send your first end-to-end encrypted message over the mesh network.
-
2026-04-05Run a Transport Node (Be a Relay for Your Community)
Set up a Reticulum Transport Node on a Raspberry Pi to relay traffic, propagate announces, and bridge LoRa radio to your local network. Be the backbone for your community mesh.
-
2026-04-05Reticulum over I2P and Tor: Maximum Privacy Networking
Route Reticulum traffic through I2P or Tor for maximum privacy. Hide your IP, bypass firewalls, and host globally reachable nodes anonymously.
-
2026-04-05Host a Decentralized Website with NomadNet
Host decentralized pages on the Reticulum network using NomadNet. Write static and dynamic content in micron markup, serve it over LoRa or the internet, no cloud required.
-
2026-04-05Go Off-Grid: Connect Sideband or MeshChat to Your RNode
Connect Sideband or MeshChat to your RNode and send your first encrypted message over LoRa radio — completely off-grid, no internet required.
-
2026-04-05Flash an RNode: Turn a $15 ESP32 LoRa Board into a Radio Modem
Turn a cheap ESP32 LoRa development board into an RNode radio modem for Reticulum. Step-by-step firmware flashing, configuration, and LoRa parameter guide.
-
2026-04-05Emergency Comms Playbook: Reticulum for Disaster Preparedness
A complete emergency communications playbook using Reticulum and LoRa. Hardware kit list, pre-configuration steps, deployment procedures, and communication protocols for when infrastructure fails.
-
2026-04-05Build a Handheld RNode (Portable Off-Grid Communicator)
Build a portable, battery-powered RNode communicator in a 3D-printed case. Complete bill of materials, assembly instructions, and phone pairing guide.
-
2026-04-05Bridge Your LoRa Island to the Internet
Build a gateway node that bridges your local LoRa mesh to the global Reticulum network over the internet. Manage bandwidth, announce rates, and firewall configuration.
-
2026-03-18Building kb-manage: A Rust CLI for Kiro's Local Knowledge Bases
I built a Rust CLI called kb-manage that reads, searches, exports, imports, and updates Kiro's local HNSW knowledge bases — reverse-engineering the on-disk format, embedding pipeline, and chunking strategy to produce binary-compatible indexes.
-
2026-03-17Reverse-Engineering Amazon Kiro CLI: What 31MB of Strings Reveals
I ran `strings` on the Amazon Kiro CLI binary and spent an evening picking through the output. Here's what I found — from embedded prompt fragments and local ML inference to the archaeology of Amazon's AI branding pivots.
-
2026-03-17Building TychoTTY: A Terminal Emulator from Scratch in Rust
I built a cross-platform terminal emulator with tmux-like multiplexing, vim-modal keybindings, an embedded WebKit browser, and an AI-augmented shell powered by a local LLM — all in ~1900 lines of Rust.
-
2026-03-11Stress-Testing My AI Assistant: 12 Phases, 5 Bugs, and a Session Poisoner
I put my custom AI assistant through a 12-phase stress test designed to break it. It found prompt injections, wrote async Python, and analyzed its own codebase — but a single failed tool call could permanently corrupt a session.
-
2026-03-11Scaling AI Products on AWS Bedrock: Getting Past the Quota Wall
AWS Bedrock's on-demand quotas are surprisingly restrictive for production use. Here's how to actually scale an AI product using AWS services — from provisioned throughput to multi-model routing and self-hosted alternatives.
-
2026-03-05Building a Virtual Microphone on macOS for STT + Video Conferencing
How to build a native macOS app that acts as a virtual microphone, letting you fork audio to both a speech-to-text agent and your video conferencing software simultaneously.
-
2026-03-05Building a Personal AI Brain: Architecture for a Self-Hosted Agent
Planning the architecture for a personalized AI agent that runs on a home server, leverages AWS Bedrock for LLM inference, and uses MCP for distributed tool execution across devices.
-
2026-02-28Reverse Prompting: A Practical Guide
Six practical approaches to reverse prompting — from output-to-prompt and role reversal to systematic reverse engineering protocols — with a decision matrix for choosing the right technique.
-
2026-02-28Building Reliable Multi-Agent LLM Systems: A Best Practice Guide
A comprehensive guide to building reliable multi-agent LLM systems, covering failure taxonomies, design principles, architecture selection, and implementation playbooks — synthesized from UC Berkeley, Google DeepMind, and Anthropic research.
-
2026-02-28Agent Steering Best Practices for Kiro CLI Custom Agents
A comprehensive guide to writing effective agent steering files, synthesized from CLAUDE.md, AGENTS.md, Cursor Rules, Kiro steering, and community best practices.
-
