Openclaw Memory Qdrant — Development skill for Claude Code
OpenClaw plugin for semantic memory with Qdrant and Transformers.js.
How to install Openclaw Memory Qdrant
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zuiho-kai/openclaw-memory-qdrant and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Openclaw Memory Qdrant does
OpenClaw plugin for semantic memory with Qdrant and Transformers.js.
Alternatives in Development
- Mempalace Search — Search your memories across the MemPalace using semantic search with wing/room filtering 58.6k ★
- Serena — Code Intelligence Advanced code navigation and semantic search 14k ★
- Agentic Stack — One brain, many harnesses 2.2k ★
README
openclaw-memory-qdrant
OpenClaw 本地语义记忆插件,基于 Qdrant 和 Transformers.js 实现零配置的语义搜索。
**📦 ClawHub**: https://clawhub.ai/skills/memory-qdrant
特性
- 🧠 本地语义搜索 - 使用 Transformers.js 在本地生成 embeddings
- 💾 内存模式 - 零配置,无需外部服务
- 🔄 自动捕获 - 通过 lifecycle hooks 自动记录重要信息
- 🎯 智能召回 - 根据上下文自动检索相关记忆
安装
通过 ClawHub(推荐)
clawhub install memory-qdrant
手动安装
cd ~/.openclaw/plugins
git clone https://github.com/zuiho/openclaw-memory-qdrant.git memory-qdrant
cd memory-qdrant
npm install
安装要求
**首次运行准备:**
**Node.js 版本**: 需要 Node.js ≥18.17
node --version # 检查版本**构建工具**(用于编译原生依赖):
- Windows: Visual Studio Build Tools
npm install --global windows-build-tools - macOS: Xcode Command Line Tools
xcode-select --install - Linux: build-essential
sudo apt-get install build-essential # Debian/Ubuntu sudo yum groupinstall "Development Tools" # RHEL/CentOS
- Windows: Visual Studio Build Tools
**网络访问**:
- 安装时需要访问 npmjs.com 下载依赖包
- 首次运行时会从 huggingface.co 下载 embedding 模型(约 25MB)
- 如果配置了外部 Qdrant 服务器,需要能访问该服务器
**原生依赖**:
sharp: 图像处理库(可能需要编译)onnxruntime: ML 推理引擎(可能需要编译)undici: HTTP 客户端(通过 @qdrant/js-client-rest 引入)
推荐安装方式
# 使用 npm ci 确保可重现的安装(推荐用于生产环境)
npm ci
# 或者分步安装(用于调试)
npm install --ignore-scripts # 跳过 post-install 脚本
npm rebuild # 然后重新构建原生模块
故障排除
**问题: 原生模块编译失败**
- 确保已安装对应平台的构建工具
- 尝试清理缓存:
npm cache clean --force - 删除 node_modules 重新安装:
rm -rf node_modules && npm install
**问题: 模型下载失败**
- 检查网络连接和防火墙设置
- 确保能访问 huggingface.co
- 模型会缓存在
~/.cache/huggingface/目录
**问题: Node 版本不兼容**
- 升级到 Node.js 18.17 或更高版本
- 使用 nvm 管理多个 Node 版本:
nvm install 18 && nvm use 18
配置
在 OpenClaw 配置文件中启用插件:
{
"plugins": {
"memory-qdrant": {
"enabled": true,
"autoCapture": false, // 默认关闭,需要时手动开启
"autoRecall": true,
"captureMaxChars
Related Skills
MemorIA
Persistent semantic memory for agents (Claude Code, Cursor, and custom agents) using MCP + Qdrant.
Collective Agent Memory
Semantic search over Claude Code / OpenClaw session history
Claude Code Semantic Memory
Persistent semantic memory system for Claude Code.
Compress
Save this Claude Code session to the vault and update the semantic memory index.
Severance
A semantic memory system designed for Claude Code.
V Memory Refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash;
Related Agents
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Part 16: autoDream — Automatic Memory Consolidation
Note: OpenClaw 2026.4+ has a built-in dreaming system (Part 22) inside memory-core. If you're on 2026.4+, use
ML Reviewer
Machine-learning expert for the code-review panel. Spawned when the diff touches ML frameworks (torch, tensorf