dsh-daoing-memory
Persistent, self-evolving memory for DeepSeek Harness agents with auditable facts, concerns, experiences, and a browser workbench.
Install
$ dsh plugin --profile web add dsh-daoing-memoryPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Stores raw session notes through the memory_fact tool.
- Extracts diary notes into durable user facts and open concerns.
- Manages experiential memory through candidate, reporting, revision, refinement, and verification flows.
- Recalls relevant experiences with keyword/situation relevance and optional context scoping.
- Injects a compact profile snapshot of facts and open concerns into the system prompt.
- Provides ledger querying and integrity verification for memory mutations.
- Includes consolidation tools for periodic store housekeeping.
- Adds a web-sidebar Memory workbench for inspecting, correcting, promoting, and deleting memories.
- Bundles a memory-extraction skill to guide agent memory extraction.
Useful For
- Preserving user preferences, background details, and unresolved concerns across DSH sessions.
- Building an agent knowledge base from corroborated task experiences.
- Reviewing or correcting memories through a browser-based human-in-the-loop workflow.
- Investigating and rolling back memory changes using an append-only audit ledger.
- Providing relevant user context to an agent without repeatedly asking for it.
Who It Fits
- DeepSeek Harness users who want persistent agent memory.
- Agent builders seeking governed semantic and experiential memory.
- Users who need manual inspection and curation of stored agent memory.
Documented Limitations
- The README states support for the web profile and describes a browser sidebar workbench.
- The bundled extraction skill requires separate placement using the provided install-skill script.
- The README instructs users to restart DSH after installation.
- Memory extraction quality depends on agent use of the bundled memory-extraction skill and memory tools.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 2 runtime, 0 development, 12 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- daoing/dsh-daoing-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 18e0009 · 2026-09-15
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-22
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Ontology-first research preset and epistemic loop plugin for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →