Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
basicmachines-co avatar

Memory Defrag

  • 534 installs
  • 25 repo stars
  • Updated April 20, 2026
  • basicmachines-co/basic-memory-skills

memory-defrag is an agent skill that compacts, deduplicates, and reorganizes long-running agent memory files by splitting bloated documents, merging duplicates, and removing stale notes so retrieval stays fast.

About

memory-defrag is a skill from basicmachines-co/basic-memory-skills that treats agent memory like a filesystem needing periodic defragmentation. It splits oversized files, merges duplicate entries, deletes stale information, and restructures the memory hierarchy when daily notes pile up without consolidation. Developers run it weekly or biweekly via cron, on demand when cleanup is requested, or when MEMORY.md exceeds roughly 500 lines. The skill keeps context windows efficient for Claude and similar agents that read markdown knowledge stores, preventing redundant or outdated notes from crowding out current facts during retrieval.

  • deduplicates redundant memories
  • reindexes fragmented knowledge
  • shrinks noisy context
  • preserves salient facts
  • speeds retrieval

Memory Defrag by the numbers

  • 534 all-time installs (skills.sh)
  • Ranked #1,701 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 1, 2026 (Skillselion catalog sync)
npx skills add https://github.com/basicmachines-co/basic-memory-skills --skill memory-defrag

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs534
repo stars25
Last updatedApril 20, 2026
Repositorybasicmachines-co/basic-memory-skills

How do you clean up bloated agent memory files?

Compact, deduplicate, and reorganize long-running agent memory so retrieval stays fast and context windows are not wasted on stale or redundant notes.

Who is it for?

Developers maintaining long-running agent MEMORY.md stores that have grown redundant, stale, or too large for efficient context retrieval.

Skip if: One-off chat sessions without persistent markdown memory files or teams storing knowledge exclusively in external databases.

When should I use this skill?

MEMORY.md exceeds about 500 lines, daily notes lack consolidation, or the user asks to defrag, reorganize, or clean agent memory.

What you get

Reorganized memory hierarchy, merged duplicate notes, pruned stale entries, and smaller consolidated markdown files for faster agent retrieval.

  • Consolidated memory files
  • Deduplicated note set
  • Restructured memory hierarchy

By the numbers

  • Recommends defrag when MEMORY.md exceeds roughly 500 lines
  • Suggests weekly or biweekly scheduled runs via cron

Files

SKILL.mdMarkdownGitHub ↗

Memory Defrag

Reorganize memory files for clarity, efficiency, and relevance. Like filesystem defragmentation but for knowledge.

When to Run

  • Periodic: Weekly or biweekly via cron (recommended)
  • On demand: User asks to clean up, reorganize, or defrag memory
  • Threshold: When MEMORY.md exceeds ~500 lines or daily notes accumulate without consolidation

Process

1. Audit Current State

Inventory all memory files:

MEMORY.md           — long-term memory
memory/             — daily notes, tasks, topical files
memory/tasks/       — active and completed tasks

For each file, note: line count, last modified, topic coverage, staleness.

2. Identify Problems

Look for these common issues:

ProblemSignalFix
Bloated file>300 lines, covers many topicsSplit into focused files
Duplicate infoSame fact in multiple placesConsolidate to one location
Stale entriesReferences to completed work, old dates, resolved issuesRemove or archive
Orphan filesFiles in memory/ never referenced or updatedReview, merge, or remove
InconsistenciesContradictory information across filesResolve to ground truth
Poor organizationRelated info scattered across filesRestructure by topic
Recursive nestingmemory/memory/memory/... directoriesDelete nested dirs (indexer bug artifact)

3. Plan Changes

Before making edits, write a brief plan:

## Defrag Plan
- [ ] Split MEMORY.md "Key People" section → memory/people.md
- [ ] Remove completed tasks older than 30 days from memory/tasks/
- [ ] Merge memory/bm-marketing-ideas.md into memory/competitive/
- [ ] Update stale project status entries in MEMORY.md

4. Execute

Apply changes one at a time:

  • Split: Extract sections from large files into focused topical files
  • Merge: Combine related small files into coherent documents
  • Prune: Remove information that is no longer relevant or accurate
  • Restructure: Move files to appropriate directories, rename for clarity
  • Update: Fix outdated facts, dates, statuses

5. Verify & Log

After changes:

  • Verify no information was lost (compare before/after)
  • Update any cross-references between files
  • Log what was done in today's daily note:
## Memory Defrag (HH:MM)
- Files reviewed: N
- Split: [list]
- Merged: [list]
- Pruned: [list]
- Net result: X files, Y total lines (was Z lines)

Guidelines

  • Back up first. If git is available, commit before defragging. If not, note the pre-defrag state.
  • Preserve raw daily notes. Don't delete or modify memory/YYYY-MM-DD.md files — they're the audit trail.
  • Target 15-25 focused files. Too few means bloated files; too many means fragmentation. Aim for the sweet spot.
  • File names should be scannable. Use descriptive names: people.md, project-status.md, competitive-landscape.md — not notes-2.md.
  • Don't over-organize. One level of directories is usually enough. memory/tasks/ and memory/competitive/ are fine; memory/work/projects/active/basic-memory/notes/ is not.
  • Completed tasks: Tasks with status: done older than 14 days can be removed. Their insights should already be in MEMORY.md via reflection.
  • Ask before destructive changes. If uncertain whether information is still relevant, keep it with a (review needed) tag rather than deleting.

Related skills

How it compares

Use memory-defrag for periodic markdown knowledge compaction; use semantic search or vector stores when memory lives outside file-based agent notes.

FAQ

When should memory-defrag run?

memory-defrag recommends weekly or biweekly cron runs, on-demand cleanup when users request reorganization, or when MEMORY.md exceeds about 500 lines or daily notes accumulate without consolidation.

What does memory-defrag change in agent memory?

memory-defrag splits oversized files, merges duplicates, removes stale entries, and restructures the memory hierarchy so agent retrieval stays fast and context windows avoid redundant markdown bulk.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.