Memory Reflect

basicmachines-co/basic-memory-skills/.agents/skills/memory-reflect

by basicmachines-co6d2b1d426d0dacf020aef45f029768c9d8c1e5e5No license24 starsListed Oct 9, 2026Updated Oct 9, 2026Repository updated 5 months ago

Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory. Use when triggered by cron, heartbeat, or explicit request to reflect on recent activity. Runs as background processing to improve memory quality over time.

Instructions onlyAI & Agents
AI-generated overview

Consolidates recent daily notes and conversations into curated long-term memory files.

What it does
Reviews the last few days of daily notes, conversation transcripts, and recently modified memory files, then decides which items are worth keeping. It writes consolidated insights into MEMORY.md, updates or removes outdated entries, and appends a short reflection log to today's daily note. It also checks for filesystem problems such as recursive nesting or orphaned files.
When to use it
Use it as a periodic background task, such as a cron or heartbeat job, to improve memory quality over time. It also fits on-demand requests to reflect, consolidate, or review recent memory, and after context window compaction events.
Requirements
Instructions only; no scripts are shipped. It needs read and write access to a memory directory containing daily notes, MEMORY.md, and optionally task files and conversation transcripts.

Memory Reflect

Review recent activity and consolidate valuable insights into long-term memory.

Inspired by sleep-time compute — the idea that memory formation happens best between active sessions, not during them.

When to Run

  • Cron/heartbeat: Schedule as a periodic background task (recommended: 1-2x daily)
  • On demand: User asks to reflect, consolidate, or review recent memory
  • Post-compaction: After context window compaction events

Process

1. Gather Recent Material

Read the last 2-3 days of daily notes from memory/YYYY-MM-DD.md. Also check:

  • Recent conversation transcripts (if accessible)
  • Any files modified in memory/ in the last 48 hours
  • Active tasks in memory/tasks/

2. Evaluate What Matters

For each piece of information, ask:

  • Is this a decision that affects future work? → Keep
  • Is this a lesson learned or mistake to avoid? → Keep
  • Is this a preference or working style insight? → Keep
  • Is this a relationship detail (who does what, contact info)? → Keep
  • Is this transient (weather checked, heartbeat ran, routine task)? → Skip
  • Is this already captured in MEMORY.md or another long-term file? → Skip

3. Update Long-Term Memory

Write consolidated insights to MEMORY.md following its existing structure:

  • Add new sections or update existing ones
  • Use concise, factual language
  • Include dates for temporal context
  • Remove or update outdated entries that the new information supersedes

4. Log the Reflection

Append a brief entry to today's daily note:

markdown
## Reflection (HH:MM)- Reviewed: [list of files reviewed]- Added to MEMORY.md: [brief summary of what was consolidated]- Removed/updated: [anything cleaned up]

Guidelines

  • Be selective. The goal is distillation, not duplication. MEMORY.md should be curated wisdom, not a copy of daily notes.
  • Preserve voice. If the agent has a personality/soul file, reflections should match that voice.
  • Don't delete daily notes. They're the raw record. Reflection extracts from them; it doesn't replace them.
  • Merge, don't append. If MEMORY.md already has a section about a topic, update it in place rather than adding a duplicate entry.
  • Flag uncertainty. If something seems important but you're not sure, add it with a note like "(needs confirmation)" rather than skipping it entirely.
  • Restructure over time. If MEMORY.md is a chronological dump, restructure it into topical sections during reflection. Curated knowledge > raw logs.
  • Check for filesystem issues. Look for recursive nesting (memory/memory/memory/...), orphaned files, or bloat while gathering material.

Source and attribution

Source:basicmachines-co/basic-memory-skillsin.agents/skills/memory-reflectat commit6d2b1d4

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal