skills.rest
jannolan200211-ship-it
jannolan200211-ship-itCOMMUNITY
Explore all skills by this author →
GitHub

memory-librarian

Organize workspace knowledge with a tiered RAM-safe memory architecture.

1|Updated Feb 15, 2026
Search Tags:#indexing#memory#workspace#archiving#ripgrep#distillation#ram
One-click install
npx skills add https://github.com/jannolan200211-ship-it/my-cosmos-backup --skill memory-librarian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-librarian
Source: https://github.com/jannolan200211-ship-it/my-cosmos-backup/tree/main/temp_setup
Command: npx skills add https://github.com/jannolan200211-ship-it/my-cosmos-backup --skill memory-librarian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ripgrep, curl.

What problem does it solve?

In RAM-constrained environments, keeping workspace knowledge organized without exhausting memory is challenging. This skill offers a RAM-safe, tiered memory system that maintains a lean global index, creates on-demand topic files, and uses fast search to keep information accessible without overloading resources.

Core Features & Use Cases

  • Tiered memory architecture (hot index, warm topics, cold workspace) for scalable knowledge management.
  • On-demand topic creation, automatic distillation, archiving, and index maintenance.
  • Fast retrieval with lightweight search and RAM-conscious operations suitable for VPS deployments.

Quick Start

Run python3 distill.py to start a full distillation cycle and organize your workspace knowledge.

Frequently Asked Questions about memory-librarian

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I organize workspace knowledge without exhausting RAM on a VPS?▼

To organize workspace knowledge without exhausting VPS RAM, use a tiered memory architecture that maintains a lean global index, distills files on-demand, and archives cold data to keep retrieval fast and memory usage low.

What is tiered memory architecture for knowledge management?▼

Tiered memory architecture separates knowledge into hot global indexes, warm on-demand topic files, and cold archived workspace files, ensuring scalable knowledge management while enforcing strict RAM safety constraints.

How do I archive and distill files into a global index automatically?▼

You can archive and distill files automatically by running a distillation cycle via the orchestration script, which processes workspace knowledge, creates topic files, and updates the lean global index.

Do I need ripgrep to search the memory index in constrained environments?▼

Yes, ripgrep is required for fast retrieval and lightweight searching across the tiered memory index, enabling RAM-conscious file searches without loading full workspace archives into memory.

Can I use bash tooling to orchestrate memory archiving workflows?▼

Yes, bash tooling is required to orchestrate full memory archiving workflows, automating the distillation cycles, index maintenance, and notifications needed for VPS deployments.

When should I use cold workspace archiving instead of keeping files active?▼

Cold workspace archiving should be used when files are no longer frequently accessed, allowing the system to distill them into the global index and free up active RAM resources.

Related Skills

Explore More Data & Analytics Skills→
capaas2capaas2

bash-linux

Execute Bash command chaining, file inspection, and process management on Linux and macOS.

Community
Intermediate
opencodosopencodos
14

qmd

Locate past conversations and decisions in an Obsidian Vault using hybrid search.

Official
Intermediate
jpcaparasjpcaparas
37

ripgrep

Search codebases and documents with ripgrep regex patterns.

Community
Advanced
xotongxotong

AgentDB Performance Optimization

Optimize AgentDB vector search with quantization, HNSW indexing, caching, and batch processing.

Community
Advanced