memory-hygieneAudit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.
Install via ClawdBot CLI:
clawdbot install dylanbaker24/memory-hygieneKeep vector memory lean. Prevent token waste from junk memories.
Audit: Check what's in memory
memory_recall query="*" limit=50Wipe: Clear all vector memory
rm -rf ~/.clawdbot/memory/lancedb/Then restart gateway: clawdbot gateway restart
Reseed: After wipe, store key facts from MEMORY.md
memory_store text="<fact>" category="preference|fact|decision" importance=0.9The main source of junk is autoCapture: true. Disable it:
{
"plugins": {
"entries": {
"memory-lancedb": {
"config": {
"autoCapture": false,
"autoRecall": true
}
}
}
}
}Use gateway action=config.patch to apply.
ā Store:
ā Never store:
Set up a monthly wipe + reseed:
cron action=add job={
"name": "memory-maintenance",
"schedule": "0 4 1 * *",
"text": "Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion"
}When using memory_store:
Generated Mar 1, 2026
A customer support AI accumulates irrelevant logs and status messages in memory, causing high token usage and slow responses. This skill helps audit and clean the memory to retain only user preferences and key issue resolutions, improving efficiency and reducing operational costs.
In a healthcare setting, an AI assistant stores transient data like appointment reminders and system heartbeats, leading to memory bloat. Using this skill, the system can be configured to auto-capture only critical patient preferences and medical decisions, ensuring compliance and faster recall of essential information.
A financial advisory bot captures raw message logs and OAuth tokens, risking security and performance. This skill enables periodic memory wipes and reseeding with key client investment preferences and regulatory decisions, maintaining lean memory for accurate, secure financial guidance.
An educational AI stores excessive lesson logs and temporary states, hindering personalized learning. By implementing memory hygiene, it can retain only student learning styles and key lesson outcomes, optimizing memory for adaptive tutoring and reducing computational overhead.
An e-commerce recommendation engine bloats with junk data like heartbeat statuses, slowing down product suggestions. This skill allows auditing and cleaning to focus on user shopping preferences and past purchase decisions, enhancing personalization speed and accuracy for better customer experiences.
Offer this skill as part of a subscription-based AI maintenance platform, providing automated memory audits and cleaning services. Revenue is generated through monthly or annual fees from businesses using AI agents, ensuring optimal performance and reduced token costs.
Provide consulting to integrate and customize memory hygiene for specific industries, such as healthcare or finance, with one-time setup fees and ongoing support contracts. Revenue comes from implementation projects and maintenance agreements tailored to client needs.
Release a free basic version for individual developers, with premium features like automated cron jobs and advanced analytics for enterprises. Revenue is generated through upgrades to paid tiers, targeting small to large organizations managing AI systems.
š¬ Integration Tip
Start by disabling auto-capture in the configuration to prevent junk accumulation, then set up a monthly cron job for automated maintenance to keep memory lean without manual intervention.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection