DSH Plugins Marketplace

DSH Plugins

Plugins

/

dsh-tool-memory

L

dsh-tool-memory

Discovered

Local knowledge-graph memory tools for DeepSeek Harness

dsh-tool-memory

English | 中文

Local knowledge-graph memory for DeepSeek Harness (dsh) as a Cordis plugin. The agent can store entities, observations, and relations in a file-backed graph, search them, and manage them across sessions — no external service and no credentials required.

Install

npm install @libai168/dsh-tool-memory

Requires @deepseek-ai/cordis (^4.0.1) and @deepseek-ai/dsh-tools (^0.1.0-rc.6) as peer dependencies.

Configuration

- name: 'github:LJH-snow/dsh-tool-memory'
  config:
    # storagePath: '~/.dsh/memory.jsonl'

The graph is stored as JSONL at storagePath (default: ~/.dsh/memory.jsonl). The file format matches the official MCP memory server shape: entity lines carry name/entityType/observations, relation lines carry from/to/relationType, so an existing memory file can be reused as-is.

Tools

ToolDescriptionWrite
memory_statsReport entity, relation, and observation counts plus storage pathNo
memory_read_graphRead the graph (entities, observations, relations)No
memory_searchSearch entities by keyword with related relationsNo
memory_create_entitiesCreate entities from a JSON arrayYes
memory_add_observationsAppend observations to one entityYes
memory_create_relationsCreate relations between existing entitiesYes
memory_delete_entitiesDelete entities and cascade their relationsYes
memory_delete_observationsDelete specific observationsYes
memory_delete_relationsDelete specific relationsYes

Security contract

  • Everything is local: the store reads and writes one JSONL file; there is no network access and no credential handling.
  • Writes are atomic (temp file + rename), and corrupt lines in an existing file are skipped on load instead of failing the plugin.
  • Relations are only created between entities that already exist, preventing dangling references.
  • Output is capped: reads return at most 200 entities and 500 relations, search returns at most 50 entities (default 20), names are capped at 200 characters and observations at 2,000 characters, and each mutating call accepts at most 100 input items.
  • All mutating tools are marked kind: 'edit'; array parameters are passed as JSON strings and validated before any write.

API scope

This version covers the full entity/relation/observation lifecycle with file storage. Timestamps, embeddings-based semantic search, and multi-store isolation are future work.

Development

npm install
npm run typecheck
npm test
npm run build
npm pack --dry-run

License

MIT

Comments

Loading…

Similar plugins

dsh-memory-graph

by zmh2000829

Local-first long-term memory and temporal knowledge graph plugin for DeepSeek Harness

Manifest valid

★ 3

MIT

TypeScript

Aug 23, 2026

dsh plugin --profile web add dsh-memory-graph

by Luke-Yong

dsh-plugin-knowledge-graph for Deepseek Harness

Tools & CapabilitiesManifest valid

★ 4

MIT

TypeScript

Aug 17, 2026

dsh plugin --profile web add dsh-plugin-knowledge-graph

by IAMLieutenant

DeepSeek Harness 用户记忆插件

Memory & ContextSessions & MessagesManifest valid

★ 3

↓ 182/wk

MIT

TypeScript

Oct 22, 2026

dsh plugin --profile web add dsh-tool-user-memory

by seriousz158

A local Git-backed long-term memory bundle for DeepSeek Harness

Memory & ContextManifest valid

★ 169

↓ 99/wk

MIT

JavaScript

Oct 10, 2026

dsh plugin --profile web add dsh-git-memory

by twoyoung91

Local personal memory and knowledge management for DeepSeek Harness. It supports local FTS, CPU-embedding or OpenAI-Compatible Embedding API.

Tools & CapabilitiesManifest valid

★ 4

MIT

TypeScript

Sep 28, 2026

dsh plugin --profile web add @dsh-external/dsh-memoknow

by YYTbit

Structured long-term memory system for DeepSeek Harness

Development & InfrastructureManifest valid

★ 5

↓ 33/wk

MIT

TypeScript

Aug 14, 2026

dsh plugin --profile web add dsh-plugin-meta-memory