dsh-memory-graph
Local-first long-term memory and temporal knowledge graph plugin for DeepSeek Harness.
Install
$ dsh plugin --profile web add "$PWD"Plugin 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
- Automatic pre-turn hybrid memory recall combining lexical match, graph proximity, time decay, and optional semantic embeddings
- Background post-turn summarization and temporal fact extraction with superseded history tracking
- Canonical entity graph management with duplicate detection, merging, aliasing, and orphan cleanup
- Interactive DSH Web visualizer and sidebar dashboard with per-turn memory latch controls
- Built-in suite of agent tools (memory_remember, memory_recall, memory_graph, memory_backup, etc.)
- JSONL snapshot export and empty-database restore with outbox replay for failed writes
Useful For
- Persisting user preferences, ongoing project contexts, and durable facts across distinct DSH sessions
- Graph-based relationship exploration and entity tracking during long-term research or multi-turn workflows
- Recovering and inspecting automated memory extraction archives without re-running full conversations
Who It Fits
- DeepSeek Harness users needing persistent personal agent memory across sessions
- Developers working on complex multi-turn workflows requiring structured knowledge graph retrieval
Documented Limitations
- Uses node:sqlite DatabaseSync, intended for single-process local stores rather than distributed high-concurrency systems
- Semantic recall requires an external OpenAI-compatible embedding endpoint (disabled by default)
- JSONL database restore operations require an empty target database to prevent data overwrites
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 1 runtime, 17 development, 11 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
- zmh2000829/dsh-memory-graph
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 4fae39c · 2026-09-18
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
- 2GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-23
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →Traceable, searchable, cross-session knowledge graph memory engine for DeepSeek Harness.
View plugin →Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
View plugin →Sandbox-first automatic permission policy and intelligent risk classification for DeepSeek Harness.
View plugin →