Memory Reflect

This is background processing for Claude's memory system, meant to run on a schedule or after big context compactions. It scans recent daily notes and conversations, filters out the noise (heartbeats, weather checks, routine stuff), and writes what actually matters into MEMORY.md. The philosophy is solid: memory formation works better between sessions than during them, so let this run overnight or between work blocks. It's opinionated about structure, merging updates into existing sections rather than appending forever. If you're building a long-running agent that needs to remember decisions and lessons without turning into a bloated archive, this handles the curation work you'd otherwise do manually.

skills.sh installs: 750
GitHub stars: 23
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add basicmachines-co/basic-memory-skills --skill memory-reflect --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Find what changed recently, then read the relevant files:

# Find recently modified notes — use json format for the complete list
# (text format truncates to ~5 items in the summary)
recent_activity(timeframe="2d", output_format="json")

# Read specific daily notes
read_note(identifier="memory/2026-02-27")
read_note(identifier="memory/2026-02-26")

# Check active tasks
search_notes(note_types=["task"], status="active")