跳到主要内容
Plugin

DLR

ljwzhaoxiaoniu/DLR

把 tsm-core-dlr 语义服务(LanceDB 向量 + 图)挂为 MCP 工具,并携带与场景无关的 DLR/TSM 建模技能、服务状态浮层与 agent 规则;该服务是硬依赖,须先运行、bundle 才能激活。

形态
Plugin 插件
安装
npm 包安装
需要密钥
是
近月下载
1,062
最近推送
今天更新

项目说明

From README

DLR Proj — Decoupled Logic Representation + Three-Level Semantic Modeling English 中文 -brightgreen) -brightgreen) DLR (Decoupled Logic Representation) is an original data-source-level semantic modeling paradigm: a two-layer model ( LE logical entities / PE physical views) plus two mechanisms ( ARCS projection anchoring, PAS semantic routing).

It decouples the logical concept layer from the physical data layer so an LLM agent can land natural-language questions on relational databases reliably.See docs/03-design.md.

The project runs DLR inside the Three-Level Semantic Modeling (TSM) framework — L1 dlr (data-source level) / L2 consensus (domain-consensus level) / L3 sop (business-logic level).The admission criteria for a piece of knowledge are the governance line.See docs/02-concept.md.

A checkout ships five npm packages — the semantic service, the dsh bundle, the exam system, and two re

Original description

DLR (Decoupled Logic Representation) + Three-Level Semantic Modeling (TSM) — a data-source-level semantic-layer paradigm, its TypeScript service (LanceDB + Neo4j), the dsh integration, and two benchmark scenarios: BIRD mini-dev (500/500) and Cloud-OpsBench (JRA 752/754).

安装方式

npm 包安装 · 需要额外配置密钥

README 解析
shell
dsh plugin --profile web add "$(pwd)/DSH-based Agent Service/dsh-tsm-agent"
shell
dsh (DeepSeek Harness: headless / web)

为什么是这个分数

近 1 天仍在推送;README 给出了可直接复制的安装命令;运行前需要准备 API Key 或环境变量;近月 npm 下载 1062 次,star 不多但真在被使用。

维护活跃
100
实用度
100
生态热度
61
上手便捷
74
信号质量
100
数据置信度
85%
评分怎么算