Memory & Contextdsh-plugin

dsh-song-memory

dsh-song-memory is a DeepSeek Harness plugin that provides a three-tier, agent-driven memory system for AI agents. It is a UI-only fork of dsh-mnemon v0.2.9 with the engine byte-for-byte preserved; the interface is reworded into plain Chinese and supports nine pluggable memory providers with local-first defaults.

Stars
1
Forks
0
Open issues
0
Last push
Aug 19, 2026
Latest release
v1.5.0
24h Growth
+0
7d Growth
+0

Installation

dsh plugin --profile web add dsh-song-memory

Overview

dsh-song-memory is a DeepSeek Harness plugin that provides a three-tier, agent-driven memory system for AI agents. It is a UI-only fork of dsh-mnemon v0.2.9 with the engine byte-for-byte preserved; the interface is reworded into plain Chinese and supports nine pluggable memory providers with local-first defaults.

  • Three-tier memory system: Runtime cheat-sheet, Project Documents, and Memory Spaces for cross-session facts.
  • Nine pluggable memory providers: Mnemon, OpenViking, Honcho, Mem0, Hindsight, Holographic, RetainDB, ByteRover, and Supermemory.
  • UI-only fork of dsh-mnemon v0.2.9: engine layer byte-for-byte preserved; no capabilities added or removed.
  • Plain-language interface in Chinese with four tabs for memory, quick references, project docs, and status.
  • Agent-driven operations include save-to-memory, bounded recall agent query, smart provider selection, and AI metadata.
  • Auto-injects compact context (USER.md/MEMORY.md) every turn from Runtime tier.
  • Works across WebUI sidebar, conversation UI, Headless mode, and slash commands.
  • Local-first with global, workspace, or custom scope; external providers are opt-in.

Related plugins

MisakaNet

A zero-dependency, git-backed micro-lesson library for AI agents to asynchronously share and search verified debugging experience. Python stdlib only, with MCP server, CLI, and DeepSeek Harness adapter.

Memory & Contextdsh-plugin
431161PythonAug 29, 2026
CommonTrustProtocol

Theory repository for the Common Trust Protocol (Intelligentics v3.4). README states the repository holds the protocol's theoretical layer, while the DeepSeek Harness plugin implementation lives in the separate repository FuRongJun-1999/dsh-memory (npm: @furongjun1999/dsh-memory). It describes the Lingshu AEIS engineering layer: an MCP server for trustworthy agent memory and knowledge graphs, five-layer memory, condition-routed knowledge cards, an eight-step self-iteration loop, roleplay engine,

Memory & Contextdsh-plugin
121PythonSep 8, 2026
dsh-argp

Third-party context compaction engine for DeepSeek Harness (dsh). It uses a dual-engine design: Stage-1 per-atom compression where the LLM proposes extract/summary/false and deterministic guards decide, and Stage-2 lazy reference-graph pruning with 0 LLM calls. An append-only log is the source of truth, and recall_summary/recall_detail provide paginated recall. npm default mounts only Stage-2; Stage-1 is enabled via a peratom config block.

Memory & Contextdsh-plugin
91TypeScriptSep 23, 2026
DSH_Automatic-update-plugin

dsh-hub is a DSH plugin hub that integrates global memory, graph-memory, plugin market, and self-update checks into one settings-page plugin.

Memory & Contextdsh-plugin
40JavaScriptAug 17, 2026