dsh-tdai-memory¶
| 类型 | 插件 | 分类 | 记忆与上下文 |
| 星数 | ⭐3 | 状态 | ✅ 活跃 |
| 能力 | coding, memory, multi-agent | 更新时间 | 2026-08-14 |
📖 项目简介¶
GitHub: Scorp1o117/dsh-tdai-memory · npm: dsh-tdai-memory A port of TencentDB Agent Memory (Tencent Cloud's open-source four-layer memory system, originally an OpenClaw plugin) into DeepSeek Harness.
✨ 核心特性¶
- L0 conversation capture: every turn (turn end, request boundary) is
- L1 structured memory: a background pipeline uses an LLM to extract
- L2 scenes / L3 persona: scene blocks and user profile generation
- Automatic recall injection: on every prompt assembly, relevant memories
- Tools:
tdai_memory_search(L1 structured search),
📦 安装¶
dsh plugin --profile web add dsh-tdai-memory
🚀 快速开始¶
- insert:
- id: tdai-memory
name: 'dsh-tdai-memory'
config: {} # keys can live in settings.yaml instead