What makes local-tencentdb-agent-memory-flash notable?

1.1K downloads. Trust evidence available

How should local-tencentdb-agent-memory-flash 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

local-tencentdb-agent-memory-flash

本地部署零依赖的 TencentDB-Agent-Memory 插件，基于 SQLite 实现对话记忆的存储和召回，支持自动清理与上下文保护。 Skill: local-tencentdb-agent-memory-flash Owner: cloudcode-hans Summary: 本地部署零依赖的 TencentDB-Agent-Memory 插件，基于 SQLite 实现对话记忆的存储和召回，支持自动清理与上下文保护。 Tags: latest:1.0.1 Version history: v1.0.1 | 2026-05-22T03:05:22.687Z | user - 新增“安装检测”步骤，建议用户先检查是否已安装插件，避免重复安装。 - 优化使用指南结构，将安装与配置流程分离，提升易读性和适用性。 - 修改安装指引：已安装用户跳过安装步骤，直接引导至配置。 - 补充操作步骤说明，强调便捷检测和配置为核心流程。 - 其他内容与原有文档保持一致。 v1.0.0 | 2026-05-21T09:53:19.827Z | user Initial releas

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K 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: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.1release · observed May 22, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176p0fdnm9khs6p3rx9vvyds583j95x:local-tencentdb-agent-memory-flash

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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-cloudcode-hans-local-tencentdb-agent-memory-flash/snapshot"

Documentation

CLAWHUB

12,015 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

skill.md

# TencentDB-Agent-Memory 本地部署指南

> **设计原则**：检测先行，避免重复安装。已安装则跳过安装步骤，直接进入配置阶段。

---

## 一、插件概述

`tencentdb-agent-memory` 是腾讯云数据库团队开源的记忆插件，为 OpenClaw 提供对话记忆能力。采用本地 SQLite + sqlite-vec 后端，**零外部依赖、零配置**即可运行。

---

## 二、安装检测（必做）

在执行任何安装操作之前，先检测插件是否已安装：

```bash
npm list -g tencentdb-agent-memory 2>&1
```

**或者更快速地检查扩展目录：**
```bash
openclaw plugins list 2>&1 | findstr memory-tencentdb
```

### 判断结果

| 检测结果 | 含义 | 下一步 |
|----------|------|--------|
| `[email protected]` 有版本号 | ✅ 已安装 | → 直接进入 **第四节：配置阶段** |
| `not found` 或空 | ❌ 未安装 | → 进入 **第三节：安装步骤** |

---

## 三、安装步骤（未安装时执行）

### Step 1：安装插件

```bash
openclaw plugins install @tencentdb-agent-memory/memory-tencentdb
```

预期输出：
```
下载并提取完成
安装到 ~/.openclaw/extensions/memory-tencentdb
依赖包已安装
插件已注册 (memory-tdai)
配置文件已更新（备份到 openclaw.json.bak）
```

### Step 2：重启 Gateway 生效

```bash
openclaw gateway restart
```

等待 10~30 秒，确认 Gateway 状态恢复「运行中/健康」。

> ⚠️ **已安装用户跳过以上两步，直接进入配置阶段。**

---

## 四、本地配置（零依赖模式）

安装完成后，配置文件 `~/.openclaw/openclaw.json` 会自动生成基础配置：

```json5
{
  "memory-tencentdb": {
    "enabled": true
  }
}
```

### 推荐完整配置（优化召回质量）

```json5
{
  "memory-tencentdb": {
    "enabled": true,
    
    // 记忆提取配置
    "extraction": {
      "enabled": true,
      "enableDedup": true,              // 防重复记忆
      "maxMemoriesPerSession": 30,      // 单次对话最多存 30 条
      "model": ""                        // 留空复用 OpenClaw 默认模型
    },
    
    // 管线节奏
    "pipeline": {
      "everyNConversations": 3,         // 每 3 轮对话触发提炼
      "enableWarmup": true,             // 新对话从第 1 轮开始
      "l1IdleTimeoutSeconds": 60,       // 停嘴 60 秒后触发提炼
      "l2DelayAfterL1Seconds": 120      // L1 完后 2 分钟归纳场景块
    },
    
    // 召回配置（影响"能不能想起"）
    "recall": {
      "enabled": true,
      "strategy": "hybrid",             // keyword + embedding 融合
      "maxResults": 8,                  // 每次注入最多 8 条记忆
      "scoreThreshold": 0.25,           // 阈值略调低，避免"啥都想不起来"
      "timeoutMs": 5000
    },
    
    // Embedding：本地用 BM25，资源充裕可配远端
    "embedding": {
      "enabled": true,
      "provider": "none"                // 默认用 SQLite 内置 BM25
      // 如需远端 Embedding，替换为：
      // "provider": "openai",
      // "baseUrl": "https://your-embedding-endpoint/v1",
      // "apiKey": "sk-xxx",
      // "model": "text-embedding-3-small",
      // "dimensions": 1536
    },
    
    // 自动清理旧日志
    "clean": {
      "enabled": true,
      "keepDays": 30,                   // L0 原始日志保留 30 天
      "cleanTime": "03:00"
    }
  }
}
```

修改后重启生效：
```bash
openclaw gateway restart
```

---

## 五、关键补丁（工具调用支持）

执行 patch 脚本确保工具调用结果能被正确记录：

```bash
cd ~/.openclaw/extensions/memory-tencentdb
bash scripts/openclaw-after-tool-call-messages.patch.sh
openclaw gateway restart
```

> 如果脚本不存在（版本差异）可跳过，基础对话内容仍会正常记录。

---

## 六、上下文保护配置

在 `openclaw.json` 中添加以下配置，防止长对话中近期决策被压缩覆盖：

```json5
{
  "agents": {
    "defaults": {
      "memoryFlush": {
        "enabled": true,
        "reserveTokensFloor": 40000,
        "softThresholdTokens": 4000
      },
      "contextPruning"

_meta.json

{
  "ownerId": "kn76zmreha127n33hcnaknnmd5834x16",
  "slug": "local-tencentdb-agent-memory-flash",
  "version": "1.0.1",
  "publishedAt": 1779419122687
}

skill-card.md

## Description:

Guides agents and users through local installation, configuration, validation, and troubleshooting of the TencentDB-Agent-Memory plugin for OpenClaw.

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

## Publisher:

[cloudcode-hans](https://clawhub.ai/user/cloudcode-hans)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and OpenClaw users use this skill to decide whether the memory plugin is already installed, install it when needed, configure local SQLite-backed memory and recall behavior, and verify that persistent memory works.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill directs users to install an unpinned third-party OpenClaw plugin.

Mitigation: Install only after confirming trust in the publisher, prefer a pinned and verified package version, and review the package before deployment.

Risk: The skill asks users to run a patch script that modifies OpenClaw behavior.

Mitigation: Inspect the patch script before running it, avoid elevated privileges, and confirm how to disable the plugin if behavior is unexpected.

Risk: The memory plugin stores conversation content, preferences, and tool-call results persistently.

Mitigation: Confirm storage expectations before use and document how to delete stored memories and logs.

Risk: Optional remote embedding configuration can send memory content to an external provider.

Mitigation: Use remote embeddings only when the provider and endpoint are approved for the data being stored.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/cloudcode-hans/skills/local-tencentdb-agent-memory-flash)
- [Publisher profile](https://clawhub.ai/user/cloudcode-hans)

## Skill Output:

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

**Output Format:** [Markdown with bash and JSON configuration snippets]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes installation checks, OpenClaw plugin commands, configuration examples, validation prompts, and troubleshooting guidance.]

## Skill Version(s):

1.0.1 (source: server release metadata)

## 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.

Github ReposUpdated 2d 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.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular