dsh-lan-memory
Run the following command in DeepSeek Harness:
dsh plugin install kiefeng/dsh-lan-memory
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install kiefeng/dsh-lan-memory in your DeepSeek Harness terminal to install this memory and persona plugin (source: https://github.com/kiefeng/dsh-lan-memory).
About this plugin
By default, a DeepSeek Harness assistant has no cross-session memory. User preferences, project context, and hard-won lessons all vanish the moment a new conversation starts. dsh-lan-memory persists that scattered knowledge into three structured tiers: a pinned layer injected in full every turn, a retrieval layer queried by keyword on demand, and an experience library that accumulates lessons and methods over time, keeping context coherent across hundreds of turns.
Beyond memory, the plugin ships an editable persona system (a static SOUL document plus a MOOD output contract), a structured mood state pool (Vibe, Sparks, Reflections, Will) on every reply, and a one-click dedup-and-merge routine. All data lives in plain JSONL files on disk with zero external databases and zero runtime dependencies; the GUI settings page lets you add, edit, and remove memory entries, tweak the persona contract, and trigger the cleanup in one click.
This plugin suits DeepSeek Harness users who want persistent memory and a stable personality without standing up an extra database or microservice stack. Whether you are a maintainer keeping long-running project context, or an indie developer who simply wants your assistant to have a fixed voice and a consistent opinion, install it and it starts working immediately.
Use Cases
- Retain user preferences and project context across sessions without repeating
- Assign a fixed personality and tone that stays consistent through long conversations
- Accumulate project lessons and methods for on-demand retrieval in future tasks
Best For
- DeepSeek Harness users who want persistent memory without an extra database
- Tech leads or architects maintaining long-running project context
- Indie developers who want a fixed personality and consistent output style for their assistant
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.