memory-maintenanceIntelligent memory management for OpenClaw agents. Reviews daily notes, suggests MEMORY.md updates, maintains directory health, and auto-cleans old files. Recommended for agents with growing memory footprints.
Install via ClawdBot CLI:
clawdbot install memory-maintenanceIntelligent memory management for OpenClaw agents. Reviews daily notes, suggests MEMORY.md updates, maintains directory health, and auto-cleans old files.
Agents wake up fresh every session. Without maintenance:
This skill automates the tedious work of keeping your agent's memory organized and actionable.
This skill works well with lightweight models. We recommend:
gemini-2.5-flash (fast, cost-effective)gemini-2.5-flash-lite (if rate limits hit)Both handle the structured output and analysis tasks efficiently.
# Install the skill
clawhub install memory-maintenance
# Configure (optional)
# Edit config/settings.json to customize schedule, retention, etc.
# Run manually
openclaw skill memory-maintenance run
# Or let it run automatically via cron (configured during install)Daily Session Notes (memory/YYYY-MM-DD.md)
↓
Review Agent (scheduled daily)
↓
Structured Suggestions (JSON)
↓
Human Review (markdown report)
↓
Approved Updates → MEMORY.md
↓
Auto-Cleanup (archive old files)agents/memory/review-v2-YYYY-MM-DD.md
# Dry run (preview)
openclaw skill memory-maintenance apply --dry-run 2026-02-05
# Apply safe changes (archiving, cleanup)
openclaw skill memory-maintenance apply --safe 2026-02-05
# Apply all (requires confirmation)
openclaw skill memory-maintenance apply --all 2026-02-05Edit config/settings.json:
{
"schedule": {
"enabled": true,
"time": "23:00",
"timezone": "Europe/London"
},
"review": {
"lookback_days": 7,
"model": "gemini-2.5-flash",
"max_suggestions": 10
},
"maintenance": {
"archive_after_days": 7,
"retention_days": 30,
"consolidate_fragments": true,
"auto_archive_safe": true
},
"safety": {
"require_approval_for_content": true,
"require_approval_for_delete": true,
"trash_instead_of_delete": true
}
}--safe--all + confirmationagents/memory/.trash/ (recoverable for retention period)# Run review manually
openclaw skill memory-maintenance review
# Apply changes
openclaw skill memory-maintenance apply [--dry-run|--safe|--all] DATE
# Run cleanup
openclaw skill memory-maintenance cleanup
# Check status
openclaw skill memory-maintenance status
# View stats
openclaw skill memory-maintenance statsThe skill suggests updates to standard MEMORY.md sections:
agents/memory/review-v2-YYYY-MM-DD.json — Structured suggestionsagents/memory/review-v2-YYYY-MM-DD.md — Human-readable reportagents/memory/stats.json — Aggregate statisticsagents/memory/archive/YYYY-MM/ — Monthly bucketsagents/memory/.trash/ — Recoverable deletionsbrew install gemini-cli)brew install jq)"Gemini failed"
→ Check GEMINI_API_KEY is set in .env or environment
"No suggestions generated"
→ Check daily notes exist in memory/YYYY-MM-DD.md
→ Review error logs in agents/memory/error-*.txt
"Too many maintenance tasks"
→ Run openclaw skill memory-maintenance apply --safe to archive old files
→ Adjust archive_after_days in config
Built by Max Hutchinson as part of an AI agent infrastructure exploration.
MIT — Free to use, modify, distribute.
Part of the Hybrid Agent Architecture. Built for agents that improve over time.
Generated Mar 1, 2026
Research assistants generate extensive daily notes from literature reviews and experimental data. This skill automatically consolidates key findings into a permanent MEMORY.md, ensuring researchers don't lose critical insights between sessions and can quickly reference past discoveries without sifting through daily logs.
Support agents handle numerous tickets daily, building context about customer issues and solutions. The skill reviews daily interaction logs, suggests updates to permanent customer protocols in MEMORY.md, and archives old cases, ensuring agents maintain consistent, up-to-date knowledge without manual note-keeping.
Content creators produce daily notes on ideas, drafts, and editorial calendars. This skill analyzes these notes to suggest permanent additions to project timelines and content strategies in MEMORY.md, while auto-archiving completed tasks, helping creators stay organized and focused on current projects.
Development teams log daily progress, bug fixes, and architectural decisions. The skill reviews these logs to suggest updates to the team's technical MEMORY.md (documenting APIs, deployment processes, etc.), ensuring institutional knowledge is preserved as team members rotate or projects evolve.
Professionals use AI assistants for scheduling, email drafting, and task management, generating daily activity logs. The skill consolidates important preferences, recurring tasks, and contact details into MEMORY.md, allowing the assistant to maintain personalized service without relearning context each session.
Offer the skill as a cloud-based service with tiered subscriptions (e.g., basic for individuals, pro for small teams, enterprise for large organizations). Revenue comes from monthly/annual fees, with premium features like advanced analytics, custom retention policies, and priority support.
Sell perpetual licenses to large enterprises, with upfront costs for installation, customization (e.g., integration with existing knowledge bases like Confluence), and ongoing support contracts. Revenue includes license fees, customization projects, and annual maintenance fees.
Provide a free version with core functionality (e.g., basic review and archiving) to attract individual users, then monetize through paid upgrades for advanced features like automated MEMORY.md updates, extended retention, and team collaboration tools. Revenue comes from premium subscriptions.
💬 Integration Tip
Start by running the skill manually to review daily notes before enabling automated scheduling, ensuring the suggestions align with your MEMORY.md structure and safety preferences.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper — gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard — runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...