DSH Plugin Hub
Memory & Contextdsh-plugin

hme-plugin

HME (Harness-Memory-Evolution) is a cross-session long-term memory plugin for DeepSeek Harness. It provides USER, MEMORY, and archive layers, recall keyword retrieval, TTL and value tiers, plus a startup banner and hme-status tool/command. Current version v0.5.1; package @yinging/dsh-hme.

Stars
2
Forks
0
Open issues
0
Last push
Aug 17, 2026
Latest release
—
24h Growth
+0
7d Growth
+0

Installation

dsh plugin --profile web add github:weopenfire-git/hme-plugin

Overview

HME (Harness-Memory-Evolution) is a cross-session long-term memory plugin for DeepSeek Harness. It provides USER, MEMORY, and archive layers, recall keyword retrieval, TTL and value tiers, plus a startup banner and hme-status tool/command. Current version v0.5.1; package @yinging/dsh-hme.

  • Cross-session long-term memory: lets DeepSeek Harness agents remember user identity, project conventions, and lessons across sessions.
  • Three-layer memory architecture: USER + MEMORY core plus archive by topic.
  • Bounded core memory with expansion archive; archive uses topic files and tag overwrite.
  • Recall keyword retrieval for archive memories.
  • TTL and value tiers: V1 never expires, V2 default 365d, V3 default 90d; rules customizable.
  • Startup banner and status dashboard; hme-status tool and /hme-status command show version, memory capacity, archive stats, and rules.
  • Writes include [v:N] value markers; model proactively writes experience with four distillation criteria.
  • Install via dsh plugin add github:weopenfire-git/hme-plugin or npm @yinging/dsh-hme; add host line in cordis.patch.yml.

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