omdsh-dev /dsh-mnemon
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
★ 1,014⑂ 71👁 0⑃ 409● 240▤ 87
+7
Daily
1,014
stars
71
forks
0
watchers
409
prs
240
issues
87
releases
README
dsh-mnemon
English · 简体中文
Composable, view-based context for DeepSeek Harness.
Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
Install and start ·
Watch the demo ·
Documentation ·
Build a plugin
Why dsh-mnemon
An Agent that starts every session from scratch keeps asking what it was already told. Putting everything into one memory store is no better: it either floods each turn or misses what matters. dsh-mnemon gives DeepSeek Harness memory that is layered, visible and composable, and skills that improve with use.
- The right memory for each turn. Preferences and working facts stay in context. Project documents and long-term evidence are searched only when a question needs them.
- You can see what a turn used. Under each reply, the turn memory bar lists the documents and memories the turn read and wrote, and one click opens each in the Memory System. The Memory System shows everything that is stored and lets you edit it.
- Save to memory in one click. When a conversation turns up a fact worth keeping, the brain mark under the reply hands it to a task Agent, which removes duplicates, distils it and writes it to the right Memory Space, or saves it where you choose: working memory, your profile or a Memory Space. The receipt says where it went.
- Skills that improve with use. Skills keeps every DSH skill in one place. It can review your real conversations, draft a better SKILL.md and backtest it before you adopt it, and it installs more skills from skills.sh, GitHub and sites that publish Agent Skills.
- Compose it on the Plugins page. Choose a main strategy and optional enhancements, and switch them without moving any data. Every component has its own page for its settings.
- Keep data where you want it. Local by default with Mnemon Native, or one of eight third-party Providers. Storage can be global, per workspace, centralized or in a directory you choose, with ZIP backup.
- Extend it. Sources and Strategies are ordinary DSH plugins built on public SDKs. An installed component gets the same pages and switches as the shipped ones.
See it in action
These recordings come from a real WebUI with the live DeepSeek model answering, on a seeded, fictional project, Lumen. Waits for the model play faster, marked in the lower right corner.
Save a new fact to memory. A reply reports a new measurement. Select the brain mark under it, cut the candidate down to the sentence worth keeping and send it to the task Agent; the receipt names the Memory Space it went to and opens it in one click.
See all memory in one place. Status, runtime memory, Project Documents and Memory Spaces live in the Memory System. The graph links memories through the entities they mention, and Ask Agent answers with the memories it cites, by content.
Compose memory on the Plugins page. One main strategy, its memory sources and optional enhancements, each switch applying atTop issues
#554[Bug]: 不兼容dsh0.2.25 comments · 2026-11-03#431[Issue]: Feature request: lossless compaction archive for context replaced by DSH compaction4 comments · 2026-10-17#584[Bug]: DSH Desktop 0.13.2 下全新安装 dsh-mnemon 0.5.41/0.5.42 失败:cosmokit resolves outside the installation closure2 comments · 2026-11-07#472[Issue]: 自进化复盘产生的子代理会话无回收机制:一次复盘留两个目录,磁盘持续累积(#435 只修了侧栏可见性,未处理落盘)2 comments · 2026-10-25#334[Feature]: 把 Mnemon 载荷同步到用户自己的 Git 仓库分支(运行时记忆 / 项目档案 / 记忆空间快照)2 comments · 2026-10-04#40Runtime Memory 变化时整块重放 USER.md/MEMORY.md,建议改为增量注入(只注入变化的条目)2 comments · 2026-08-18#635[Bug]: Idle Review stops being scheduled after DSH Desktop restart; persisted attempt watermark never advances1 comments · 2026-11-13#537[Issue]: 技能管理进化页增加「一键发布自建技能到插件市场」/ One-click publish of self-authored skills from the Evolution tab1 comments · 2026-11-02
Latest release
v0.5.46: Composable Memory Plugins v0.5.46 2026-11-14v0.5.46: Reliable Memory Tasks and Workspace Controls / 更可靠的记忆任务与工作区控制 - Preserve collapsed skill directories across catalog refreshes (630; fixes 627). - Add an optional quiet memory graph while retaining the current default (631; closes 628). - Bound repeated long-session reads without losing historical activity (633; fixes 632). - Initialize memory-child guards and lifecycle observers reliably (634; fixes 629). - Recover bounded first-step review admission failures and expose redacted diagnostics (637; refs 635, which remains open). - Allow one correction of malformed completion JSON in th