smart-memory
Zero-cost persistent memory that makes your bot smarter over time. Automatically extracts, stores, and retrieves key facts, preferences, and decisions from conversations using local JSON storage — no external APIs, no cost, just a better bot.
Why use this skill?
Enhance your OpenClaw agent with Smart Memory. Locally store user preferences, project facts, and instructions to ensure your AI gets smarter over time.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jcools1977/openjaw-smart-memoryWhat This Skill Does
The Smart Memory skill for OpenClaw transforms your AI agent from a stateless assistant into a context-aware partner. It provides a persistent, zero-cost, local storage mechanism that allows the agent to recall user preferences, project-specific details, and past decisions across multiple sessions. By automatically extracting key data points—such as preferred tech stacks, communication styles, and ongoing project status—the agent builds a deepening understanding of the user over time. Everything is managed locally via shell scripts, ensuring that your data never leaves your machine, preserving both privacy and performance.
Installation
To add this capability to your agent, run the following command in your terminal:
clawhub install openclaw/skills/skills/jcools1977/openjaw-smart-memory
Once installed, the memory-manager.sh script will be available at ~/.openclaw/smart-memory/, providing an interface for your agent to read, write, update, and prune stored memory files.
Use Cases
- Project Continuity: Maintain state for ongoing coding projects, remembering which frameworks or database configurations were chosen for a specific repository.
- Personalization: Automatically adapt to the user's preferred tone, coding standards (e.g., 'always use type hints in Python'), and environment settings like light or dark mode.
- Knowledge Retrieval: Keep track of important deadlines, team members' names, or specific business logic instructions that the user mentioned days or weeks ago.
- Correction Management: Handle evolving requirements gracefully by updating stale information with new instructions while keeping an audit trail of changes.
Example Prompts
- "Remember that for all my upcoming web projects, I want to use Tailwind CSS instead of raw CSS."
- "What was the decision we made last week regarding our database architecture for the analytics dashboard?"
- "Actually, please stop assuming I work in the office; I am working remotely for the foreseeable future."
Tips & Limitations
To get the most out of Smart Memory, ensure your agent is prompted to proactively scan for new information to cache. While this tool is incredibly powerful for local context, remember that 'low' confidence memories should be verified if they trigger significant actions. Since storage is local, manual cleanup of the ~/.openclaw/smart-memory/ directory is possible if your history grows too large. Avoid storing highly sensitive data like plain-text passwords here, as the files are stored as standard JSON.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jcools1977-openjaw-smart-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-write, file-read
Related Skills
autodream-core
通用记忆整理引擎 — 基于适配器模式的跨平台记忆整理技能。自动去重、合并、删除过时条目。| Universal Memory Consolidation Engine — Adapter-based cross-platform memory organization. Auto-dedup, merge, prune stale entries.
context-compressor
Intelligently compress context — conversations, code, logs. Preserve key information while reducing token usage. Auto-detects content type and applies optimal compression.
auto-context
智能上下文卫生检查器。分析当前会话的上下文污染程度 (长对话、主题漂移、噪声累积),建议:continue、/fork、/btw 或新会话。 支持手动触发(/auto-context)和自动触发(响应层实现)。 基于 ArXiv 论文和认知心理学研究的多维度评估体系。
memory-stack
AI 记忆栈架构 - 符合 2026 前沿的 AI 记忆系统。微调+RAG+ 上下文三层设计,mirrors 人类记忆工作方式。
less-token
Save 40-65% tokens on summarization tasks. Compress verbose summary prompts into structured one-line instructions. Text-to-text translator only — no CLI, no API key, no install, no external dependencies. Works on ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, zero dependencies.