记忆核心（Memory Eternal）：自研的 DeepSeek Harness 记忆插件，不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault（自研去重、自研 CJK 检索、可 git 管理），设置页提供图形化知识库（统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗），Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

DeepSeek Harness Web UI plugin for fluid streaming rendering and silky scrolling. 流畅流式渲染与丝滑滚动。

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.

官方 DeepSeek Harness 的交互式终端 UI 插件：自研 ANSI 极简渲染核心（由作者自己的开源项目天枢 Tui 演进）、流式 Markdown/工具卡、多会话 tab、16+ 主题、slash 命令与选择器、输入历史与本地偏好持久化、LSP 诊断、成本统计、启动自更新。纯展示层。

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.