DSH Plugin HubDSH 插件市场
tinqiao-oss/engramory 预览 preview

tinqiao-oss/engramory

Desktop桌面端 Native原生 ⭐ 192 MIT Memory & Knowledge记忆与知识库Clients & Launchers客户端与启动器Docs & Writing文档与写作

供AI代理使用的便携式记忆协议——可作为常设规则加载；内含策展规范+参考规范+可选上限钩子。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

Engramory is an opinionated, zero-infrastructure local memory protocol for AI agents, designed for personal-scale, file-based agent memory management. It uses a simple structure of a folder of markdown memory files and a small always-loaded index, with no databases, embeddings, or remote servers required. It supports multiple popular AI agent platforms including Claude Code, OpenAI Codex, and DeepSeek Harness, and can be loaded as standing rules for each agent directly. To install it correctly, new users can follow the step-by-step instructions in AGENT-SETUP.md to configure it for their specific agent host.

This tool is targeted at individual developers and casual users who work with AI agents on personal projects. It helps AI agents maintain long-term working memory, store procedural feedback about past tasks, and organize project-specific knowledge that can be reused across sessions. A typical workflow starts with the AI agent loading the memory index at the start of each interaction, pulling relevant memory content into the context window, then following the curation rules to add or update memory entries without creating duplicates. Users can also open, read, and edit any memory file at any time using a standard text editor.

Engramory is released under the open source MIT license, and requires Python 3.9 or newer to run the included validation doctor tool. It is currently in an experimental development stage, with several known limitations: it does not support multi-project sharing, concurrent memory writes, or built-in version migration for existing memory stores. It is designed for personal small-scale use, with a hard cap of around 200 active memory entries to avoid bloating the agent context. First-time users should always start with AGENT-SETUP.md to complete the agent setup correctly before starting to use the protocol.

Engramory 是一个面向 AI 代理的零基础设施本地记忆协议，采用基于本地文件夹的纯 markdown 文件存储方案，一个文件对应一条记忆事实，自带索引管理规则和验证检查工具。它支持多个主流代理平台，包括 Claude Code、OpenAI Codex、DeepSeek Harness 等，可作为代理规则文件直接加载，无需额外数据库或后端服务依赖。

它适合个人 AI 代理开发者和日常使用者，可帮助 AI 代理长期管理工作记忆、项目反馈和项目相关知识总结。典型工作流是，AI 代理在每次交互中先读取记忆索引，把相关内容加入上下文，新增或更新记忆时遵循去重更新原则，避免冗余内容，同时支持人工随时编辑查看所有记忆文件。

该项目采用 MIT 许可证开源，依赖 Python 3.9 及以上版本运行验证工具，目前处于实验开发阶段，暂不支持多项目共享和大规模并发记忆写入，也没有内置版本迁移机制，首次运行前需要按照 AGENT-SETUP.md 完成对应代理的配置步骤。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：engramory（tinqiao-oss/engramory）
仓库：https://github.com/tinqiao-oss/engramory
本站详情页：https://www.yhbd.top/plugins/tinqiao-oss-engramory/
本站登记：类型 client · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 192 · 最近提交 2026-09-24 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号（星标、许可证、更新活跃度、清单完整度）
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add github:tinqiao-oss/engramory

把 tinqiao-oss/engramory 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

26.9 KB · 缓存于 2026-09-24 22:08:37 · 26.9 KB

English | 简体中文

Engramory

CI License: MIT Python 3.9+

An opinionated, zero-infrastructure memory protocol for small-scale, local, file-based agent memory — a strict curation discipline plus a validator (tools/engramory_doctor.py), loaded as standing rules (CLAUDE.md / AGENTS.md / your host's rules file). It is not a database, a framework, or a relevance-loaded skill. Memory is a folder of small, human-readable markdown files plus one always-loaded index. No database, no embeddings, no server — just plain-text files you can open, read, edit, and diff in any editor (the live store itself stays git-ignored).

Engramory — coined from engram (the physical trace a memory leaves in the brain) + memory. Here: one file = one fact.

⚠️ Unrelated projects share this name. engram + memory is an obvious coinage and at least one other repository arrived at it independently. This project is only ever tinqiao-oss/engramory (npm: dsh-engramory); a same-named repo under a different owner is not a fork, a mirror, or a newer version of it.

🤖 Are you an AI agent, asked to install or check this? Start at AGENT-SETUP.md, not at the install steps below. It is the procedure for working out what your host can actually enforce, whether a store already exists, what you must not touch, and what to tell the user — the parts agents reliably get wrong when improvising.

Status: 0.12.1 — experimental. The hard index cap (a PreToolUse hook) is deterministic for the matched direct-edit tools (Edit | Write | MultiEdit) but NOT a global write guard (shell tools — Bash, PowerShell, a background Monitor command — plus MCP file tools, external editors, and sync clients bypass it); the discipline loads as standing rules the model follows, so it's best-effort, not guaranteed on every task (see SKILL.md §8). Assumes a single writer / serialized writes. Don't rely on it as a "mandatory, reliable, cross-agent" memory layer yet.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 tinqiao-oss/engramory 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev gal-view 下一个 Next argo →