What makes Semantic Memory Search notable?

1.2K downloads. Trust evidence available

How should Semantic Memory Search be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Semantic Memory Search

为 OpenClaw Markdown 记忆文件添加向量驱动的语义搜索。使用 memsearch 库，支持混合搜索（稠密向量 + BM25），SHA-256 智能去重，本地 embedding 无需 API Key。 Skill: Semantic Memory Search Owner: sunnyhot Summary: 为 OpenClaw Markdown 记忆文件添加向量驱动的语义搜索。使用 memsearch 库，支持混合搜索（稠密向量 + BM25），SHA-256 智能去重，本地 embedding 无需 API Key。 Tags: latest:1.1.0 Version history: v1.1.0 | 2026-03-30T08:47:51.117Z | user 索引范围扩展(MEMORY.md+根目录文件)+精简SKILL.md+修package.json v1.0.0 | 2026-03-14T08:36:47.921Z | auto Initial release of semantic-memory-search. - Adds vector-driven semantic search for OpenC

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.0release · observed Mar 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s17fjpqtn9hq161hmqw21rtg8583grks:semantic-memory-search

Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-sunnyhot-semantic-memory-search/snapshot"

Documentation

CLAWHUB

13,775 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: semantic-memory-search
slug: semantic-memory-search
version: 2.0.0
description: 为 OpenClaw 记忆文件添加向量驱动的语义搜索。使用 memsearch 库，支持混合搜索（稠密向量 + BM25)，SHA-256 智能去重，本地 embedding 无需 API Key。
本地运行，完全离线。
每天自动索引。
author: sunnyhot
license: MIT
homepage: https://github.com/sunnyhot/semantic-memory-search
keywords:
  - memory
  - search
  - semantic
  - vector
  - memsearch
metadata:
  openclaw:
    requires:
      bins: ["python3"]
    optionalBins: ["memsearch"]
---

# Semantic Memory Search

为 OpenClaw 记忆文件提供本地语义搜索，无需 API Key。

 使用 `memsearch` 命令行工具。

 支持索引 memory/ 目录和根目录下的 MEMORY.md、USER.md 综文件。

 混合搜索（向量 + BM25 + RRF 重排序) SHA-256 智能去重。

 增量更新。

## 命令令```bash
# 篇引记忆文件（默认）
KMP_DUPLICATE_LIB_OK=TRUE ~/Library/Python/3.14/bin/memsearch index \
  ~/.openclaw/workspace/memory/ \
  ~/.openclaw/workspace/MEMORY.md \
  ~/.openclaw/workspace/USER.md \
  ~/.openclaw/workspace/TOOLS.md \
  ~/.openclaw/workspace/AGENTS.md
```

### 语义搜索

```bash
KMP_DUPLICATE_LIB_OK=TRUE ~/Library/Python/3.14/bin/memsearch search "你的搜索词"
```

### Cron 自动索引

每天 2:30 自动索引，结果推送到 Discord。

 手动索引:`KMP_DUPLICATE_LIB_OK=TRUE ~/Library/Python/3.14/bin/memsearch index` 即可。

 如果没有变更，输出 `已索引 N chunks， 无需操作`。Cron ID: `2ad149da-b593-458f-8eee-5976326b0238`

README.md

# 🔍 Semantic Memory Search

**为 OpenClaw 记忆文件添加语义搜索能力**

[![ClawHub](https://img.shields.io/badge/ClawHub-semantic--memory--search-blue)](https://clawhub.com/skills/semantic-memory-search)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

---

## 痛点

OpenClaw 的记忆以纯 Markdown 文件存储。这对可移植性和人类可读性很好，但：
- ❌ 没有搜索功能
- ❌ 只能 grep（仅关键词，会漏掉语义匹配）
- ❌ 将整个文件加载到上下文（浪费 token）

你需要一种方式来问"我关于 X 做了什么决定？"并获得精确的相关片段。

---

## ✨ 功能

| 功能 | 说明 |
|------|------|
| 语义搜索 | 通过语义而非关键词找到相关记忆 |
| 混合搜索 | 稠密向量 + BM25 全文检索 + RRF 重排序 |
| 智能去重 | SHA-256 哈希，未更改文件不重新嵌入 |
| 本地运行 | 无需 API Key，完全离线 |
| 自动同步 | 文件变更时自动重新索引 |

---

## 🚀 快速开始

### 1. 安装依赖

```bash
pip3 install "memsearch[local]"
```

### 2. 索引记忆文件

```bash
cd ~/.openclaw/workspace/skills/semantic-memory-search/scripts
./index.sh
```

### 3. 搜索记忆

```bash
./search.sh "Discord 频道重组"
```

---

## 📊 搜索示例

| 查询 | 说明 |
|------|------|
| "我们选了什么缓存方案？" | 即使没有"缓存"关键词也能找到 |
| "Discord 频道重组" | 找到所有相关决策和过程 |
| "播客制作流程" | 找到播客相关的所有记忆 |
| "财报跟踪配置" | 找到财报系统的配置历史 |

---

## 🔧 配置

配置文件：`~/.memsearch/config.toml`

```toml
[milvus]
uri = "~/.memsearch/milvus.db"

[embedding]
provider = "local"
model = "all-MiniLM-L6-v2"

[search]
top_k = 5
```

---

## 📁 文件结构

```
semantic-memory-search/
├── SKILL.md              # 技能说明
├── README.md             # 使用文档
├── package.json          # 包信息
├── LICENSE               # MIT 许可证
├── .gitignore            # Git 忽略文件
├── scripts/
│   ├── index.sh          # 索引脚本
│   └── search.sh         # 搜索脚本
└── config/
    └── settings.json     # 配置文件
```

---

## 🔗 相关链接

- [memsearch GitHub](https://github.com/zilliztech/memsearch)
- [memsearch 文档](https://zilliztech.github.io/memsearch/)
- [Milvus](https://milvus.io/)
- [用例来源](https://github.com/AlexAnys/awesome-openclaw-usecases-zh/blob/main/usecases/semantic-memory-search.md)

---

## 📝 更新日志

### v1.0.0 (2026-03-14)
- ✅ 初始版本
- ✅ 本地 embedding 支持
- ✅ 语义搜索功能

---

## 📄 许可证

MIT License

_meta.json

{
  "ownerId": "kn79e7737znkq4877n6wc93wn58292v9",
  "slug": "semantic-memory-search",
  "version": "1.1.0",
  "publishedAt": 1774860471117
}

skill-card.md

## Description:

Adds vector-driven semantic search for OpenClaw Markdown memory files using memsearch with hybrid dense-vector and BM25 retrieval, SHA-256 deduplication, and local embeddings without an API key.

This skill is ready for commercial/non-commercial use.

## Publisher:

[sunnyhot](https://clawhub.ai/user/sunnyhot)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and OpenClaw users use this skill to index local Markdown memory files and retrieve semantically related memory snippets with memsearch.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can index private OpenClaw memory content, and documented Discord reporting conflicts with the offline privacy claim.

Mitigation: Review configuration before enabling integrations, confirm exactly what is sent externally, and disable or audit Discord reporting before use.

Risk: Installing or running memsearch without version controls can change retrieval behavior or dependency exposure over time.

Mitigation: Install in an isolated environment with pinned versions and review the generated index location before indexing sensitive files.

## Reference(s):

- [Semantic Memory Search on ClawHub](https://clawhub.ai/sunnyhot/skills/semantic-memory-search)
- [memsearch GitHub](https://github.com/zilliztech/memsearch)
- [memsearch Documentation](https://zilliztech.github.io/memsearch/)
- [Milvus](https://milvus.io/)
- [Semantic Memory Search Use Case](https://github.com/AlexAnys/awesome-openclaw-usecases-zh/blob/main/usecases/semantic-memory-search.md)

## Skill Output:

**Output Type(s):** [text, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with shell commands and terminal text output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Search results depend on local memory files, the memsearch installation, and configured top_k.]

## Skill Version(s):

1.1.0 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

config/settings.json

{
  "memory_path": "~/.openclaw/workspace/memory/",
  "memsearch_path": "~/Library/Python/3.14/bin/memsearch",
  "discord_channel": "1482296953445289985",
  "milvus_uri": "~/.memsearch/milvus.db",
  "embedding": {
    "provider": "local",
    "model": "all-MiniLM-L6-v2"
  },
  "search": {
    "top_k": 5
  },
  "watch": {
    "enabled": false,
    "interval_seconds": 60
  }
}

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.