deepseek-harness-forge-plugins#forge-memory

by jinguanghai

GitHub ↗

0 记忆github 检测到 manifest package.json#dsh收录于 08-14

基于 BM25 关键词检索的记忆召回。

BM25 keyword-based memory recall.

安装

$ dsh plugin --profile web add github:jinguanghai/deepseek-harness-forge-plugins#path:/plugins/forge-memory

GitHub 源码安装：首次需按提示配置 allowBuilds 构建授权后重试

安装与环境配置指引、插件开发教程见 DSH 中文社区文档 ↗

安装即在你的机器上以你的权限运行第三方代码——它可读写文件、使用凭据、访问网络，DSH 的工具审批不会为插件代码加沙箱。「检测到 manifest」仅代表发现 dsh.bundle / dsh.plugin 清单，不构成兼容性或安全审查；安装前请审阅源码，不熟悉的插件先在不含密钥的环境试用。

README

BM25 experience recall for DeepSeek Harness — the 铸剑炉 (Forge) memory discipline as a plugin: keep the context short, pull in only what is relevant.

Tool	Purpose
`memory_recall`	BM25-ranked recall of past key findings (top-K, fresh-window aware)
`memory_save`	Atomic save of a key finding (tmp + rename, keeps `.bak`)
`memory_fold`	Fold a long section into a short index entry
`memory_fold_deep`	Deep-read a folded section back to full content

Data lives in memory.json / .forge-temp/memory_current.json / data/memory_current.json — bring your own memory file (empty templates in data/). No npm dependencies.

原始 README： https://github.com/jinguanghai/deepseek-harness-forge-plugins/blob/main/plugins/forge-memory/README.md ↗