Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after ClawHub install. No setup required - just install and memory_search works immediately, gets better after optional sync.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install vector-memory或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install vector-memory⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/vector-memory/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: vector-memory description: Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after ClawHub install. No setup required - just install and memory_search works immediately, gets better after optional sync. ---
Smart memory search that automatically selects the best method:
Zero configuration required. Works immediately after install.
npx clawhub install vector-memoryDone! memory_search now works with automatic method selection.
node vector-memory/smart_memory.js --syncAfter sync, searches use neural embeddings for semantic understanding.
// Same call, automatic best method
memory_search("James principles values")
// If vector ready: finds "autonomy, competence, creation" (semantic match)
// If not ready: uses keyword search (fallback)Auto-selects best method
Parameters:
query (string): Search querymax_results (number): Max results (default: 5)Returns: Matches with path, lines, score, snippet
Get full content from file.
Index memory files for vector search. Run after edits.
Check which method is active.
| Feature | Built-in | Vector | Smart Wrapper | |---------|----------|--------|---------------| | Synonyms | ❌ | ✅ | ✅ (when ready) | | Setup | Built-in | Requires sync | ✅ Zero config | | Fallback | N/A | Manual | ✅ Automatic |
Immediate (no action needed):
node vector-memory/smart_memory.js --search "query"Better quality (after sync):
# One-time setup
node vector-memory/smart_memory.js --sync
# Now all searches use vector
node vector-memory/smart_memory.js --search "query"| File | Purpose | |------|---------| | smart_memory.js | Main entry - auto-selects method | | vector_memory_local.js | Vector implementation | | memory.js | OpenClaw wrapper |
None required.
Optional environment variables:
export MEMORY_DIR=/path/to/memory
export MEMORY_FILE=/path/to/MEMORY.md安装 vector-memory 后，可以对 AI 说这些话来触发它
Help me get started with vector-memory
Explains what vector-memory does, walks through the setup, and runs a quick demo based on your current project
Use vector-memory to smart memory search with automatic vector fallback
Invokes vector-memory with the right parameters and returns the result directly in the conversation
What can I do with vector-memory in my documents & notes workflow?
Lists the top use cases for vector-memory, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/vector-memory/ 目录（个人级，所有项目可用），或 .claude/skills/vector-memory/（项目级）。重启 AI 客户端后，用 /vector-memory 主动调用，或让 AI 根据上下文自动发现并使用。
vector-memory 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
vector-memory 可免费安装使用。请查阅仓库了解许可证信息。
Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after ClawHub install. No setup required - just install and memory_search works immediately, gets better after optional sync.
vector-memory 属于「Documents & Notes」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my documents & notes tasks using vector-memory
Identifies repetitive steps in your workflow and sets up vector-memory to handle them automatically