用于在 OpenClaw 环境中安装、配置并验证 @tencentdb-agent-memory/memory-tencentdb 插件。当用户提到"安装记忆插件""配置 memory-tencentdb""开启长期记忆/召回"或出现相关报错时应触发。
How to install tencentdb-agent-memory?
tencentcloud/tencentdb-agent-memory
$npx -y skills add tencentcloud/tencentdb-agent-memory --skill tencentdb-agent-memoryInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/tencentcloud/tencentdb-agent-memory" --skill "tencentcloud/tencentdb-agent-memory"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/tencentcloud/tencentdb-agent-memory" that are relevant to the current task. Run `npx skills add "https://github.com/tencentcloud/tencentdb-agent-memory"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <img src="./assets/images/logo.png" alt="TencentDB Agent Memory" width="880" /> |
| 4 | |
| 5 | ### Agents remember,Humans innovate. |
| 6 | |
| 7 | <a href="https://trendshift.io/repositories/29310?utm_source=repository-badge&utm_medium=badge&utm_campaign=badge-repository-29310" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/29310" alt="TencentCloud%2FTencentDB-Agent-Memory | Trendshift" width="250" height="55"/></a> |
| 8 | |
| 9 | [](https://www.npmjs.com/package/@tencentdb-agent-memory/memory-tencentdb) |
| 10 | [](./LICENSE) |
| 11 | [](https://nodejs.org/) |
| 12 | [](https://github.com/openclaw/openclaw) |
| 13 | [](https://hermes-agent.nousresearch.com/docs/) |
| 14 | [](https://discord.gg/dJQM6mKMF) |
| 15 | |
| 16 | [Highlights](#-highlights) · [Overview](#overview) · [Core Technology](#core-technology-reject-flat-storage-embrace-layering-and-symbolization) · [Features](#-features) · [Quick Start](#quick-start) |
| 17 | |
| 18 | <div align="center"> |
| 19 | |
| 20 | [**English**](./README.md) · [简体中文](./README_CN.md) |
| 21 | |
| 22 | </div> |
| 23 | |
| 24 | |
| 25 | </div> |
| 26 | |
| 27 | --- |
| 28 | |
| 29 | ## ✨ Highlights |
| 30 | |
| 31 | > **TencentDB Agent Memory = symbolic short-term memory + layered long-term memory.** |
| 32 | > |
| 33 | > - **Symbolic short-term memory** offloads heavy tool logs and condenses them into compact Mermaid symbols, cutting token usage and improving task success. |
| 34 | > - **Layered long-term memory** distills fragmented conversations into structured personas and scenes, instead of flat vector piles. |
| 35 | |
| 36 | When integrated with OpenClaw, it cuts token usage by up to **61.38%**, improves pass rate by **51.52%** (relative), and raises PersonaMem accuracy from **48%** to **76%**. |
| 37 | |
| 38 | | Memory Capability | Benchmark | OpenClaw Success | With Plugin | Relative Δ | OpenClaw Tokens | With Plugin Tokens | Relative Δ | |
| 39 | | :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | |
| 40 | | **Short-term** | WideSearch | 33% | **50%** | **+51.52%** | 221.31M | **85.64M** | **−61.38%** | |
| 41 | | **Short-term** | SWE-bench | 58.4% | **64.2%** | **+9.93%** | 3474.1M | **2375.4M** | **−33.09%** | |
| 42 | | **Short-term** | AA-LCR | 44.0% | **47.5%** | **+7.95%** | 112.0M | **77.3M** | **−30.98%** | |
| 43 | | **Long-term** | PersonaMem | 48% | **76%** | **+59%** | — | — | — | |
| 44 | |
| 45 | > These results are measured over continuous long-horizon sessions, not isolated turns. For example, SWE-bench runs 50 consecutive tasks per session to simulate the context-accumulation pressure of real-world long-horizon agents. |
| 46 | |
| 47 | --- |
| 48 | |
| 49 | ## Overview |
| 50 | |
| 51 | **Memory is not about hoarding everything in the AI — it is about sparing humans from having to repeat themselves.** |
| 52 | |
| 53 | In practice, we constantly re-explain the same SOPs, project background, tool conventions, and output formats to the Agent. Such information should not require repetition, nor should it be indiscriminately dumped into the context. |
| 54 | |
| 55 | TencentDB Agent Memory helps the Agent learn your workflows, retain task context, and reuse past experience. We reject both brute-force history accumulation and irreversible lossy summarization. Instead, we design memory as a layered system: **symbolic memory** for in-task information overload, and **memory layering** for cross-session experience. |
| 56 | |
| 57 | > **Let the Agent remember what should be remembered, so people can focus on judgment, creation, and work that truly matters.** |
| 58 | |
| 59 | --- |
| 60 | |
| 61 | ## Core Technology: Reject Flat Storage, Embrace Layering and Symbolization |
| 62 | |
| 63 | Our architecture rests on two pillars: **memory layering** and **symbolic memory**. Together they ensure Agents do not merely "remember more", but "reason better". |
| 64 | |
| 65 | ### 1. Memory Layering: Progressive Disclosure with Heterogeneous Storage |
| 66 | |
| 67 | Traditional memory |
Related
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site.Jul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing.Jul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data.Jul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product.Jul 2026
- ai-seoWhen the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.Jul 2026
- ad-creativeWhen the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising…Jul 2026
