An on-demand memory index, section lookup and original-text retrieval.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-10-24
License
MIT
01What can it help you accomplish?
Retrieve earlier work from the same DSH workspace
An on-demand memory index, section lookup and original-text retrieval.
DSH users sharing context across workspace sessions
02How to install into DeepSeek Harness
Prerequisites
- DSH 0.2.0-rc.2 is the tested version; Node.js ≥ 22.12.0 is required.
Installation steps
- 01
Run `dsh plugin --profile desktop add dsh-workspace-recollection` for the desktop profile, then reopen the desktop app.
$ dsh plugin --profile desktop add dsh-workspace-recollection
Verify the integration
- Open the memory panel from the session header or the Memory settings page.
03DSH integration and capability boundaries
A DSH plugin shares long-term memory across sessions within each workspace.
Layered memory retrieval
An on-demand memory index, section lookup and original-text retrieval.
04Who is it for? When not to use it?
Good for
- DSH users sharing context across workspace sessions
Not for
- Memories are partitioned by workspace cwd; there is no global layer spanning workspaces.
- Retrieval uses a local embedding model downloaded on first start; AI summaries make an additional model call.
- Data is stored under `$DSH_HOME/session-memory/`, with a `Memory.md` file in each workspace root.
- DSH 0.1.x is incompatible; each workspace is limited to 500 entries.
05Compatibility, maintenance and safety notes
- Memories are partitioned by workspace cwd; there is no global layer spanning workspaces.
- Retrieval uses a local embedding model downloaded on first start; AI summaries make an additional model call.
- Data is stored under `$DSH_HOME/session-memory/`, with a `Memory.md` file in each workspace root.
- DSH 0.1.x is incompatible; each workspace is limited to 500 entries.
README author claims only.
06Frequently asked questions
How do I enable this memory plugin in DSH?
Run `dsh plugin --profile desktop add dsh-workspace-recollection` for the desktop profile, then reopen the desktop app.
How does DSH retrieve a long memory?
An on-demand memory index, section lookup and original-text retrieval.
Do all DSH workspaces share one memory store?
Memories are partitioned by workspace cwd; there is no global layer spanning workspaces.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
webnovel-writer
by lingfengqaq
A long-form Chinese web-novel writing assistant for Claude Code and DeepSeek Harness, designed to reduce memory loss and hallucinations in serialized projects of up to 2 million characters.
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
08Data and sources
给 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 的**跨会话长期记忆**：按**工作区**隔离、**跨会话**共享。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-10-24. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.