liu-longterm-memoryUltimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Install via ClawdBot CLI:
clawdbot install louiseliu/liu-longterm-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://gitee.com/your-username/my-memoryUses known external API (expected, informational)
api.openai.comAI Analysis
The skill's architecture includes external API calls (OpenAI) and optional cloud backup to Gitee, which could raise privacy concerns depending on data sensitivity. However, these are documented features consistent with its memory system purpose, and no overt malicious patterns like credential harvesting or obfuscation are evident in the provided snippet.
Generated May 8, 2026
Developers using Cursor, Claude Code, or GitHub Copilot can maintain long-term memory across sessions. The system auto-recalls past decisions, user preferences, and project context, eliminating repetitive explanations and reducing errors.
Individuals can use the memory layers to build a personal knowledge base that evolves over time. Hot RAM keeps current tasks, warm store enables semantic search, and cold store archives decisions and learnings, all backed up automatically.
AI-powered customer support agents can remember past interactions, customer preferences, and resolved issues. This enables personalized responses and faster resolution, improving satisfaction and reducing escalation.
Researchers can use the system to store insights from papers, track hypotheses, and link related findings. The vector search helps retrieve relevant facts, and the knowledge graph captures structured relationships.
Project managers and teams can use the memory system to keep track of decisions, action items, and project history. Each session captures updates, and the curated archive provides a human-readable log of progress.
Offer a free tier with local memory storage (e.g., up to 1000 vector entries) and a paid subscription for cloud backup, multi-device sync, and unlimited storage. Revenue comes from monthly or annual subscriptions.
License the memory system to enterprises that want to embed persistent memory into their own AI agents or workflows. Provide SDK, API access, and premium support.
Create a marketplace where users can share and sell pre-built memory templates tailored to specific domains (e.g., customer support, coding, research). Revenue from listing fees or per-download charges.
💬 Integration Tip
Start with the CLI tool to set up the memory layers in an existing project. Use the auto-extraction rules to let the AI agent populate memory automatically without manual effort.
Scored May 8, 2026
Audited Apr 17, 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.
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...