memory-guardian-agentAgent workspace memory lifecycle management via 10 MCP tools + batch maintenance. Manages MEMORY.md, memory/ directory, meta.json, quality gate, Bayesian dec...
Install via ClawdBot CLI:
clawdbot install 5rbdmak7f-alt/memory-guardian-agentGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://example.com/path?q=1AI Analysis
The skill is a memory management system for a local workspace and the only flagged external URL ('https://example.com/path?q=1') is a placeholder, not evidence of real data exfiltration. The 'UNSAFE_SHELL' signal appears to be a false positive from a code example (eval) within documentation, not an active tool behavior.
Audited Apr 17, 2026 · audit v1.0
Generated May 23, 2026
An AI assistant workspace accumulates memories over time, leading to bloat and quality degradation. This skill automates memory decay, compaction, and quality checks, ensuring optimal performance and relevance.
Legal AI systems manage case files that must be audited for staleness and validity. Using memory-guardian, stale cases are automatically retired or flagged for review, maintaining a compliant and efficient case base.
Healthcare AI agents store patient interaction memories that must be regularly pruned and quality-checked to prevent data bloat and ensure accurate recall. This skill schedules maintenance and compaction tasks.
Customer support AI systems rely on a dynamic memory of past interactions. memory-guardian ensures that outdated or low-importance memories are decayed and archived, keeping the knowledge base fresh and responsive.
Offer a monthly subscription that provides automated memory maintenance, quality gate monitoring, and case lifecycle management for AI agent workspaces. Revenue comes from recurring subscription fees.
Charge per diagnostic run (memory_status, quality_check, case_query) for clients who perform ad-hoc maintenance. Revenue scales with usage frequency.
Provide end-to-end management of AI memory lifecycle, including installation, cron scheduling, and periodic compaction. Revenue from service contracts or monthly retainers.
💬 Integration Tip
Ensure MG_WORKSPACE env var points to the agent workspace root. Integrate the access_log.jsonl signal loop for accurate decay tracking.
Scored May 23, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...