Memory & Contextdsh-plugin

dsh-memory

Cross-session memory plugin for DeepSeek Harness: automatic capture prompts, per-workspace daily notes, block-level memory search with optional vector fusion, zero dependencies.

Stars
1
Forks
0
Open issues
0
Last push
Aug 22, 2026
Latest release
v0.2.4
24h Growth
+0
7d Growth
+0

Installation

dsh plugin --profile web add "github:zhouzhencheng07/dsh-memory"

Overview

Cross-session memory plugin for DeepSeek Harness: automatic capture prompts, per-workspace daily notes, block-level memory search with optional vector fusion, zero dependencies.

  • Round-by-round system prompt reminder instructs the agent to use the memory tool when new cross-session-worthy content appears (can be disabled).
  • Path-locating memory tool: returns today’s memory file for the current workspace, auto-creates with a session source comment; no parameters.
  • File operations are delegated to host native read/write/edit tools, respecting the same sandbox and pre-read observations as the model.
  • memory_search tool: title-aware block retrieval with breadcrumbs, layered keyword scoring, and 30-day half-life decay.
  • Optional vector search upgrades to hybrid keyword + vector RRF fusion (k=60) using Ollama-compatible embeddings; auto-fallback if unavailable.
  • Per-workspace daily notes stored as $DSH_HOME/dsh-memory/YYYY-MM-DD/<workspace>.md; no state files, auto-switches at midnight.
  • Plugin settings card in the UI writes to settings.yaml with hot reload; no restart required for config changes.
  • Zero npm dependencies, zero build, pure ESM; @deepseek-ai/* packages are resolved from the running dsh instance.

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