dsh-layered-memory
Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.
Install
dsh plugin --profile web add dsh-layered-memory
For reproducible installs, append #commit to pin a specific revision.
Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.
No highlight list provided; see the repository README.
- Install and start DeepSeek Harness:
npx @deepseek-ai/dsh web - Run the install command above (the CLI resolves the plugin and verifies its source)
- Confirm with dsh plugins list; restart Harness if required
Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, and check for destructive commands or excessive access. This site only indexes; it does not vouch for third-party plugins.
| Repository | github.com/JunNanLYS/dsh-layered-memory |
| License | Not declared (see repo) |
| Primary language | — |
| Downloads | 5,419 |
| GitHub stars | 17 |
| Last push | — |
| Cataloged | 2026-08-18 |
| Category | Memory |
Facts come from a public catalog snapshot (2026-09-16); descriptions are rewritten by us.
Sources: the public DeepSeek Harness plugin catalog and each plugin's GitHub repository. This is an independent third-party directory with no affiliation to or endorsement from DeepSeek, High-Flyer, or the plugin authors.
