Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every session, plus a project tree sidebar.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:lanyun077/dsh-project
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
DeepSeek Harness 的「项目」插件：把多个文件夹 + 多个会话 + 一份共享记忆/指令收敛到一个项目实体，作为叠加层补齐 DSH 缺失的"项目"概念（不改内核）。
能力
- 收纳性：侧边栏「项目」入口 → 项目树（项目 → 文件夹 → 会话）。一个项目可挂多个文件夹（每个自动注册为工作区），会话可拖入/移出。
- 项目内新建会话：在项目的任意文件夹里一键新建会话（复用
workspaces.connectWorkspace）。 - 记忆互通：项目级
PROJECT.md共享记忆——本项目所有会话开始时整体注入；agent 用project_memory_write工具追加、project_context读概览。 - 项目指令：项目级
AGENTS.md注入本项目每个会话的 system-prompt 段（热重载）。 - 工具：
project_memory_write、project_context。
架构
| 半 | 文件 | 说明 |
|---|---|---|
| host | index.js |
cordis 插件：/api/dsh-project/* 路由、工具注册、project:context system-prompt 段 + agent/pre-step 记忆注入、公告 |
| host | store.js |
ProjectStore：~/.dsh/projects/<id>/（project.json + AGENTS.md + PROJECT.md），原子写 |
| browser | client.js |
ModuleLoader bundle：侧边栏入口（DOM 注入）+ center-column 项目面板（独立 React 根）+ fetch API |
数据模型
~/.dsh/projects/<id>/
├── project.json # { id, name, description, folders:[{path,workspaceId}], sessionIds, archived, ... }
├── AGENTS.md # 项目指令（注入系统提示）
└── PROJECT.md # 项目共享记忆（会话开始整体注入）
注入
project:contextsystem-prompt 段（text为函数，按context.scope（agent）动态渲染当前项目）：项目名/简介/文件夹/AGENTS.md。agent/pre-step：把PROJECT.md快照 prepend 到会话第一条用户消息。
安装
本地插件，参考 DSH 插件装载约定（cordis.patch.yml + profile node_modules 解析）：
- 让
dsh-project可被 profile 解析（如file:../dsh-project依赖或 node_modules 软链）。 - 在 profile 的
cordis.patch.yml加：- insert: - id: project name: 'dsh-project' - 重启 DSH web（
dsh web）。
限制 / 已知取舍
- 会话显式归属项目（在「项目」面板创建/加入），不按目录自动推断。
PROJECT.md为整体注入（无向量检索），保持精简；结构化检索留待 v2。- v1 不做项目级 MCP/技能/默认模型/跨会话子任务派发。
Links
More in this category
vectorize-io/hindsight#coding-agents★ 42988
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 38990
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
agentscope-ai/ReMe#dsh★ 3534
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2682
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1093
Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
adoresever/graph-memory★ 633
Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.