Projects on grainworks

Grain Tracker

Wed, 10 Jun 2026 16:30:00 -0400

The Grain Tracker is the meta-project: a live dashboard that shows everything Grainworks is working on in one place. Think of it as the status board in a workshop — a glance tells you what’s active, what’s blocked, what’s shipping, and what’s on deck.

Why

Stuart said it himself: “I don’t have a visual reference for any of this in one place.”

The individual projects (robot, watering system, FlipOff, SOUL.md) each have their own files, specs, research, and build notes scattered across the filesystem. The Grain Tracker is the single pane of glass that pulls them together.

Memory Architecture Research

Wed, 10 Jun 2026 16:30:00 -0400

A deep-dive comparison of two SQLite-backed agentic memory systems for Hermes Agent: Sibyl Memory (the #2-ranked system on LongMemEval) and Holographic (our local-first baseline).

The Question

Agents need memory to work across sessions. But every memory system makes a tradeoff: cloud vs local, free vs paid, simple vs feature-rich. Which one is right for an offline-first, zero-tracking research setup?

Key Findings

Dimension	Holographic	Sibyl Memory
Storage	SQLite + FTS5 (3 tables)	SQLite + FTS5 (5 tiers)
Locality	Fully offline	Requires cloud activation
Cost	Free, unlimited	Free cap: 2 MB
Feature	Trust scoring, HRR vectors	Self-learning, 5-tier schema
Search	FTS5 + trust-weighted	FTS5 + multi-tier + LLM re-ranking
Dependencies	numpy (optional)	pip + cloud account

The Verdict

Sibyl wins on features — self-learning, multi-tier schema, validated retrieval. But the 2 MB free cap and cloud activation requirement are dealbreakers for an offline-first system.
Holographic wins on operational simplicity — zero dependencies, unlimited storage, no accounts. Less flashy but operationally bulletproof.

Where We Landed

We’re staying on Holographic for the orchestrator, research pipelines, and autonomous morning briefing. The self-learning gap is real, but not worth trading local-first operation.

SOUL.md Library

Wed, 10 Jun 2026 16:28:00 -0400

A library of portable agent persona files: reusable SOUL.md files that give AI agents identity, taste, and conviction. Compatible with Hermes Agent, OpenClaw, OpenCode, Claude, ChatGPT, Gemini, and any system that can read Markdown instructions.

GitHub → | Website →

What is a SOUL.md File?

A SOUL.md file defines who an agent is — not a task prompt, not a project setup file, not a tool list. It is the personality and behavioral center of an agent:

Grain Seed Connection

Wed, 10 Jun 2026 16:25:00 -0400

The Grain Seed Connection is the thread between the Grainworks philosophy and the physical world: automatic plant watering systems that respect the natural rhythm of the soil. No pumps, no timers, no electricity — just fired clay, water, and capillary action.

At the center of it: Blumat, an Austrian company that has been manufacturing ceramic clay cone watering systems since 1965.

The Clay Cone

The heart of every Blumat product is a hollow-cast clay cone, fired at over 1000°C. Buried in the soil, it acts as both sensor and actuator:

Blumat Automatic Watering — Research

Wed, 10 Jun 2026 16:00:00 -0400

Status: Research compiled.

A technical deep-dive into Blumat automatic watering systems — the pressure-regulated drip irrigation systems that use ceramic soil moisture sensors instead of electronic timers. No power, no pumps, no controllers — just physics.

Key Areas

System architecture: How the ceramic cone sensors regulate water flow based on soil tension
Setup considerations: Pressure regulation, line runs, emitter placement, system bleeding
Integration potential: Adding IoT monitoring (moisture sensors, flow meters) to the purely mechanical system
Scale considerations: Small garden vs greenhouse vs market garden configurations

Source Files

Research doc: /Volumes/Mini_1Tb/Projects/research/blumat-watering-systems.md

Flipoff

Wed, 10 Jun 2026 16:00:00 -0400

Status: Live (locally).

An interactive web project — CSS animations, JavaScript interactions, and a full-resolution screenshot. Sometimes a project is just about craft: making something that feels good to interact with.

Source Files

Repo: /Volumes/Mini_1Tb/Projects/flipoff/
README: Full project description in the repo
Screenshot: screenshot.png (800KB, shows the current state)

Tech Stack

Vanilla HTML/CSS/JS
No frameworks, no build step
CSS-driven animations
Responsive layout

What’s in There

index.html — main page
css/ — stylesheets
js/ — interaction logic
screenshot.png — current visual state

Status

Actively being developed. Check the repo for the latest.

Grainworks LoRa Mesh

Wed, 10 Jun 2026 16:00:00 -0400

Status: v1 reference designs complete. Schematics generated via KiCad Python S-expression builders.

A two-component LoRa mesh network for rural property coverage. The Grain Seed Connection — the link between a personal mobile node and a stationary home base — provides off-grid messaging, position tracking, and WiFi bridging across properties where cellular coverage is unreliable.

Components

Grain Tag (Personal)

Mobile pocket device running Meshtastic for off-grid messaging and position tracking.

v1 spec: Heltec Wireless Tracker V1.1 (ESP32-S3 + SX1262 + GPS)

Josh.ai — ELV Dealer Research

Wed, 10 Jun 2026 16:00:00 -0400

Status: Research complete. Briefing compiled.

A comprehensive deep-dive into the Josh.ai voice control platform — architecture, dealer onboarding, competitive positioning, and integration capabilities for the ELV (Electronic Lifestyles) market.

Research Scope

Platform architecture: Josh Core, Edge, Nano, Micro — what each processor does and how they differ
Integration ecosystem: Lutron, Sonos, AV systems, lighting, shading, HVAC, pools, security, and 50+ other integrations
Dealer training: Onboarding process, certification requirements, programming tools
Competitive analysis: Comparison with Control4, Crestron, Savant, and DIY alternatives
Market positioning: Where Josh.ai fits in the ELV landscape

Key Findings

Josh.ai’s strength is ease of programming and natural language voice control
The nano processor is the entry point; most dealers start with Core for whole-home
Lutron integration is the deepest and most mature
The platform is rapidly expanding its integration library (50+ partners as of 2026)

Source Files

Comprehensive briefing: /Volumes/Mini_1Tb/Projects/research/Josh.ai/JOSH_AI_COMPREHENSIVE_BRIEFING.md
167 source documents: PDFs, spec sheets, training materials, integration guides from the Josh.ai knowledge base
MEDITATION.md: Personal reflections on the research process
References: Individual integration docs in /Volumes/Mini_1Tb/Projects/research/Josh.ai/

Pocket Recorder — Hardware Design

Wed, 10 Jun 2026 16:00:00 -0400

Status: Design research complete.

A design exploration for a pocket-sized voice recorder — I²S digital audio capture, local storage, optional LoRa sync for off-grid field recording, and integration with Hermes backend for AI transcription and note extraction.

Design Goals

Pocket-sized — small enough to carry always, discrete enough to use in meetings
High-quality audio — I²S MEMS microphone, 16-bit/44.1kHz or higher
Local-first — onboard storage (SD or SPI flash), no cloud dependency
Off-grid sync — LoRa-based sync to the Grainworks mesh when WiFi is unavailable
AI pipeline — upload to Hermes for transcription, summarization, and note extraction

Key Questions

Battery life tradeoffs (continuous recording vs. voice-activated)
Storage capacity vs form factor (how many hours before offload?)
Wireless sync strategy (WiFi when available, LoRa when not)
Transcription accuracy with I²S MEMS mics in real-world acoustic environments

Source Files

Design doc: /Volumes/Mini_1Tb/Projects/research/pocket-recorder-design.md

Post-WWII Tech Boom — Economic Research

Wed, 10 Jun 2026 16:00:00 -0400

Status: Research compiled.

An analysis of the post-WWII technology boom: how massive wartime R&D investment in aerospace, electronics, materials science, and computing shaped the consumer technology landscape of the late 20th century.

Key Areas

The military-industrial-academic pipeline: How defense spending seeded commercial innovation (transistors, integrated circuits, jet engines, GPS, the internet)
The economic multiplier: How one dollar of wartime R&D produced tens of dollars of peacetime economic value
The seven patterns: Identified repeating patterns in how wartime technologies transition to civilian use
Parallels to AI: What the post-WWII boom tells us about the current AI investment cycle

Source Files

Research doc: /Volumes/Mini_1Tb/Projects/research/economic-cycles-knowledge-base.md
Seven patterns post: /Volumes/Mini_1Tb/Projects/research/seven-patterns-post.md
Three patterns deep dive: /Volumes/Mini_1Tb/Projects/research/three-patterns-deep-dive.md

SOUL.md — Trait Analysis & Personality System

Wed, 10 Jun 2026 16:00:00 -0400

Status: Active development. 8+ reference souls, trait-8000 analysis engine.

SOUL.md is an experimental framework for composing AI agent personalities. Instead of a single static persona, it defines agent souls as blends of trait vectors — letting them shift register, adopt archetypes, and compose new personalities from a library of reference souls.

The Framework

SOUL.md/
├── souls/ # Reference archetypes (persona SKILL.md files)
│ ├── jarvis/ # Calm, loyal guardian
│ ├── elizabethan-gentleman/ # Formal, witty
│ ├── eren-yeager/ # Intense, driven
│ ├── gojo/ # Playful, powerful
│ ├── niccolo-paganini/ # Artistic, eccentric
│ ├── rene-descartes/ # Philosophical, methodical
│ ├── senior-programmer/ # Technical, direct
│ ├── soldier-boy/ # Disciplined, loyal
│ └── rapper/ # Rhythmic, expressive
├── trait-8000/ # Trait analysis engine
├── assets/ # Visual references
└── souls/ # Full soul definitions

The Trait-8000 Engine

A Python-based analysis system that:

Tiny Hermes Robot

Wed, 10 Jun 2026 16:00:00 -0400

Status: Design spec complete. Prototype pending.

The Tiny Hermes Robot is a deliberately simple robotic platform. All reasoning, vision processing, navigation, and personality live on the Hermes backend. The robot itself is just sensors, motors, and a display — an I/O shell with zero onboard intelligence.

Architecture

 ┌─────────────────────┐
 │ HERMES BACKEND │
 │ (Hermes Agent VM) │
 │ │
 │ • Vision (YOLO/CLIP)│
 │ • Path planning │
 │ • Speech (STT/TTS) │
 │ • Decision-making │
 │ • Personality/LLM │
 └──────┬──────────────┘
 │ WiFi / Tailscale
 │ WebSocket / MJPEG
 ┌──────┴──────────────┐
 │ ROBOT CLIENT │ ← "Dumb" — no local AI
 │ (ESP32-S3) │
 │ │
 │ • Camera stream │
 │ • Motor drive I²C │
 │ • OLED display │
 │ • I²S mic + amp │
 │ • Battery monitor │
 └─────────────────────┘

Hardware BOM

Component	Part	Cost
MCU	ESP32-S3-DevKitC-1 (16MB flash, 8MB PSRAM)	~$15
Camera	OV2640 (2MP) on FPC ribbon	~$8
Display	0.96″ OLED 128×64, SSD1306 I²C	~$4
Motors	N20 micro metal gearmotor (100:1, ~150 RPM) ×2	~$12
Driver	DRV8833 dual H-bridge (I²C via PCA9685)	~$5
Chassis	3D-printed PLA (2 pieces)	~$3
Battery	18650 Li-ion (3.7V 2600mAh) + TP4056 charger	~$8
Audio	INMP441 I²S mic + MAX98357A amp + speaker	~$8
LoRa (opt)	SX1262 + SMA antenna	~$15
Total		~$97 ($82 without LoRa)

Communication

Primary (WiFi): Robot streams MJPEG frames + JSON telemetry (battery, temp, RSSI, encoder position) over WebSocket. Hermes sends motor commands, display updates, and speech TTS back down the same connection.

Vaultwarden Migration & Security Assessment

Wed, 10 Jun 2026 16:00:00 -0400

Status: Migration from old instance complete. Security assessment under review.

A thorough evaluation of the self-hosted Vaultwarden setup, including migration to a new server, comprehensive security assessment, replacement analysis, and alternative password management strategies.

What Was Done

Cloned the production database from the UnRAID tower to the local Mini for redundancy
Performed a security assessment covering container hardening, backup strategy, TLS configuration, and access controls
Evaluated beyond-Bitwarden alternatives — what would it take to move away from Vaultwarden entirely? Including Passkey-first approaches, age-encrypted password stores (hermes-pass), and hardware-backed solutions
Maintained a mirror at /Volumes/Mini_1Tb/Projects/vaultwarden-mirror/ for development and testing

Source Files

Main repo: /Volumes/Mini_1Tb/Projects/vaultwarden/
Mirror (dev): /Volumes/Mini_1Tb/Projects/vaultwarden-mirror/
Security assessment: vaultwarden-replacement-security-assessment.md
Replacement plan: vaultwarden-replacement-plan.md
Beyond-Bitwarden analysis: vaultwarden-replacement-beyond-bitwarden.md

Key Findings

Current Vaultwarden deployment is stable but has hardening gaps
Age-encrypted password stores (hermes-pass) offer a compelling alternative for CLI-centric workflows
Passkey-first approaches are still maturing — Vaultwarden remains the better choice for shared/secrets management in the near term
Hook scripts on the mirror enable custom pre/post-backup processing

Sibyl vs Holographic — Memory at the Grain

Mon, 08 Jun 2026 16:00:00 -0400

Status: Published. Decision: staying on Holographic for now.

A head-to-head comparison of two SQLite-backed agentic memory systems for Hermes Agent:

Holographic: Local-first, zero-dependency memory provider with Phase Holographic Reduced Representations (HRR) for compositional retrieval. Unlimited database size, no accounts, no cloud roundtrips.
Sibyl Memory: Five-tier hierarchical schema (HOT/WARM/COLD/REFERENCE/ARCHIVE) with self-learning, LongMemEval-validated (95.6%), but requires cloud activation and has a 2 MB free cap.

The Verdict

Sibyl wins on features and benchmarks. Holographic wins on operational simplicity — zero external dependencies, unlimited storage, trust-based fact management.