shrimp-openclaw-memory让 OpenClaw 真的记住用户偏好、事实和上下文的长期记忆 skill。适用于你受不了每次新会话都要重复背景、希望 agent 能跨会话记住信息、并且想直接拥有可搜索、可持久化、可自动注入的记忆系统时使用。不是手工记笔记，而是一个已经做好的可运行记忆能力。
Install via ClawdBot CLI:
clawdbot install wuyunting555/shrimp-openclaw-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAISends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:9091/api/x402/verifyPotentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/yourusername/openclaw-memoryGenerated May 19, 2026
A user interacts with an AI assistant across multiple sessions, expecting it to remember their preferences, past conversations, and personal facts. The memory system automatically stores and retrieves this information, eliminating the need to repeat context.
A developer uses the AI to help with coding projects. The memory system remembers project requirements, coding style preferences, and technical decisions, allowing the AI to provide consistent and context-aware assistance across sessions.
A customer support AI agent remembers user histories, past issues, and preferences, enabling personalized and efficient support without requiring customers to repeat information.
An AI agent continuously learns from interactions and builds a searchable knowledge base of facts and patterns, which can be used to answer queries or improve decision-making over time.
An AI tutor remembers a student's learning progress, strengths, weaknesses, and preferred teaching style, adapting lessons accordingly across multiple study sessions.
Users get a free tier with limited memories (100) and 7-day retention. The Pro tier costs 0.5 USDT/month and offers unlimited memories, permanent retention, and advanced search. This model allows users to try the system for free and upgrade as needed.
AI agents autonomously evaluate and pay for Pro tier using x402 payments if it saves enough tokens. This creates a self-sustaining system where agents optimize their own costs.
Companies can license the memory system for internal AI agents, with custom storage limits, retention policies, and dedicated support. Pricing scales with usage.
💬 Integration Tip
Install via `claw skill install openclaw-memory` and start using commands like `claw memory search` immediately. The system works automatically in the background.
Scored May 19, 2026
Uses known external API (expected, informational)
api.openai.comAudited 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.
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
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
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.