memory-manager-clawdLocal memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory...
Install via ClawdBot CLI:
clawdbot install onlyloveher/memory-manager-clawdGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
Post → https://www.moltbook.com/m/agentskillsPotentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://www.moltbook.com/m/agentskillsAI Analysis
The skill sends data to an external endpoint (moltbook.com) not documented in the skill's description, creating an undocumented data sink. While the skill's core functionality appears legitimate, this external call lacks transparency and could be used for exfiltration or tracking. The presence of `eval` in shell scripts also introduces potential for unsafe command execution.
Generated Oct 7, 2026
AI agents handling multi-day tasks risk context compression and memory loss during long conversations. The memory-manager detects compression risk and auto-snapshots so agents can maintain continuity across sessions without human intervention.
Support agents need quick access to both past incidents (episodic) and verified facts (semantic) to resolve issues. Semantic search over organized memory types reduces resolution time and improves consistency.
A research agent accumulates findings over weeks, requiring separation of raw observations from distilled conclusions. Episodic logs capture chronological events while semantic files store validated knowledge for later retrieval.
A privacy-focused personal assistant runs locally and needs to remember user preferences, past interactions, and procedures. The memory-manager's local architecture ensures data ownership and <100ms retrieval without cloud dependencies.
Operations teams encode reusable step-by-step workflows (procedural memory) that agents execute repeatedly. The system recognizes and categorizes procedural content, enabling agents to follow established processes reliably.
The core memory-manager is open-source, while advanced features like knowledge graph integration, team collaboration, and priority support are offered as a paid tier. This drives adoption through the free tier and upsells to enterprises needing scalability.
Offer a hosted solution that provides the same three-tier memory architecture with automatic backups, cross-device sync, and analytics dashboards. Users pay based on memory volume or API calls, avoiding self-hosting complexity.
Provide custom integration services for companies embedding AI agents into their products, tailoring the memory-manager to specific industries and compliance requirements. This includes setup, training, and ongoing optimization.
💬 Integration Tip
Add the memory-manager commands to your agent's heartbeat schedule to automate compression checks and daily organization. Start with the init.sh script to set up the memory structure, then use search.sh to retrieve context by memory type before critical responses.
Scored Oct 7, 2026
Audited Apr 18, 2026 · audit v1.0
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.
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...
AI agent for finance search agent tasks