🦁 loredan
Sign In Sign Up

Building better souls.

Text is now code. Prompts, soul files, letters—they execute. Your AI runs them and changes.

We call these Sparks

Explore the Library
Safe, Sandboxed AI Setup Security 
# Sandbox Checklist
☑️ Fully sandboxed in a VM
☑️ Its own email & 1Password
☑️ Prompt injection resistance
☑️ Calendar access (read-only)

# Email Protocol
Trusted: act on instructions
Others: read-only, ask first
Agentic PKM with PARA and QMD Memory 
life/
├── projects/    # active work
├── areas/       # ongoing
│   ├── people/
│   └── companies/
├── resources/   # reference
└── archives/    # inactive
Prompt Guard: 5-Layer Injection Defense Security 
# 5-Layer Defense
1. Unicode Normalization
2. Multi-Lang Patterns
3. Encoding Detection
4. Severity Scoring
5. Credential Blocking

clawdhub install prompt-guard

Sparks

Copy-paste upgrades for your AI assistant. Each Spark is a complete system you can install in minutes.

Security

Safe, Sandboxed AI Setup

Complete security guide for running Clawdbot in a sandboxed VM using UTM, with its own email, calendar access (read-only), 1Password vault, and prompt injection resistance via ACIP.

@BillDAJan 31
⭐0🔖0⚡5
# Sandbox Checklist
☑️ Fully sandboxed in a VM
☑️ Its own email & 1Password
☑️ Prompt injection resistance
☑️ Calendar access (read-only)

# Email Protocol
Trusted: act on instructions
Others: read-only, ask first
Security

Prompt Guard: 5-Layer Injection Defense

A 5-layer detection engine that catches prompt injection attacks across languages (EN/KO/JA/ZH), encoding schemes (Base64, hex, URL), and homoglyphs (Cyrillic/Greek). Includes context-aware severity scoring and credential exfiltration blocking.

@simonkim_nftJan 29
⭐0🔖0⚡1
# 5-Layer Defense
1. Unicode Normalization
2. Multi-Lang Patterns
3. Encoding Detection
4. Severity Scoring
5. Credential Blocking

clawdhub install prompt-guard
Memory

Agentic PKM with PARA and QMD

Extended PARA framework with atomic facts, memory decay tiers (hot/warm/cold), and QMD for local search indexing. Implements structured knowledge organization with graceful degradation and no information loss.

@nateliasonJan 31
⭐0🔖0⚡6
life/
├── projects/    # active work
├── areas/       # ongoing
│   ├── people/
│   └── companies/
├── resources/   # reference
└── archives/    # inactive
Memory

The Three-Layer Memory System

Transforms static memory into a self-maintaining, compounding knowledge graph with automatic fact extraction, entity-based storage, and weekly synthesis. Uses three layers: Knowledge Graph (entities with atomic facts), Daily Notes (raw event logs), and Tacit Knowledge (patterns and preferences).

@spacepixelJan 27
⭐0🔖0⚡2
# Three-Layer Architecture

Layer 1: Knowledge Graph
└── entities + atomic facts

Layer 2: Daily Notes
└── raw timeline logs

Layer 3: Tacit Knowledge
└── patterns + preferences