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