Memory Curator

Solves the context reset problem when you run /new or switch sessions. You get scripts to append to daily logs (what you built, decisions you made, bugs you fixed), extract summaries from session JSONL files before wiping state, and search through past logs when you need to remember "how did I solve that GraphQL caching issue last month." The weekly extraction workflow is smart: pull patterns that show up 3+ times or took over an hour to solve into a curated MEMORY.md, skip the one-off hacks. Honestly feels like something you'd build yourself after the third time you lost important context mid-project, except someone already wrote the tooling.

skills.sh installs: 205
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add irangareddy/openclaw-essentials --skill memory-curator --agent claude-code

Installs into .claude/skills of the current project.

Files

Memory Curator

Systematic memory management for agents through daily logging, session preservation, and knowledge extraction.

Quick Start

Log Today's Work

# Append to today's log
python scripts/daily_log.py \
  --workspace ~/.openclaw/workspace \
  --entry "Implemented user authentication with JWT" \
  --category "Key Activities"

# Show today's log
python scripts/daily_log.py --workspace ~/.openclaw/workspace --show

Search Memory

# Search all memory files
python scripts/search_memory.py \
  --workspace ~/.openclaw/workspace \
  --query "GraphQL"

# Search recent logs only (last 7 days)
python scripts/search_memory.py \
  --workspace ~/.openclaw/workspace \
  --query "authentication" \
  --days 7

# Show recent logs
python scripts/search_memory.py \
  --workspace ~/.openclaw/workspace \
  --recent 5

Extract Session Summary

# Generate summary from current session
python scripts/extract_session.py \
  --session ~/.openclaw/agents/<agent-id>/sessions/<session-id>.jsonl \
  --output session-summary.md