A DeepSeek Harness bundle plugin that adds persistent, offline, self-consolidating memory: local Markdown storage, background auto-consolidation, and cross-session recall, with your data never leaving your machine.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-30
License
MIT
01What can it help you accomplish?
Give DeepSeek Harness agents persistent memory across chat sessions
The AI remembers discussed projects, mentioned preferences, and past decisions even after the window is closed
Developers and agents running DeepSeek Harness who want continuity between conversations
Keep a private, offline memory store that self-consolidates over time
Local Markdown memory files with background deduplication, merging, and archival
Privacy-conscious users who want local, human-editable, zero-network memory
02How to install into DeepSeek Harness
Prerequisites
- Node 24+ (the plugin uses node:sqlite)
Installation steps
- 01
$ dsh plugin --profile web add @modusensus/dsh-mneme
- 02
$ dsh web
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Registers as a DeepSeek Harness bundle plugin in the `web` profile via `dsh plugin --profile web add @modusensus/dsh-mneme`; memory is persisted as local Markdown files and consolidated in the background by autoDream.
Cross-session memory injection
chat conversations in DeepSeek Harness→persistent memories injected into new sessions
Writes memories as local Markdown files on diskAuto-consolidation (autoDream)
stored memories→refined memory store via background deduplication, merging, and archival
Runs background processing to dedupe, merge, and archive memoriesFully offline local storage
memory text→local Markdown files; local embeddings/retrieval when embedProvider is set to local
Session lifecycle control
session deletion events→memories retained or pruned per sessionLifecycleEnabled config
04Who is it for? When not to use it?
Good for
- Developers and agents running DeepSeek Harness who want continuity between conversations
- Privacy-conscious users who want local, human-editable, zero-network memory
Not for
- The config table lists `embedProvider` default `openai`; to guarantee fully offline operation the docs instruct changing it to `local`, otherwise a remote OpenAI-compatible API is used for embeddings.
05Compatibility, maintenance and safety notes
- Requires Node 24+ because the plugin relies on node:sqlite; older Node versions are not supported.
- The config table lists `embedProvider` default `openai`; to guarantee fully offline operation the docs instruct changing it to `local`, otherwise a remote OpenAI-compatible API is used for embeddings.
MIT · actively maintained (latest release v0.7.3, 2026-08-29)
06Frequently asked questions
How do I install dsh-mneme with DeepSeek Harness?
Run `dsh plugin --profile web add @modusensus/dsh-mneme` and then `dsh web`. The plugin registers as a bundle plugin in the `web` profile.
What are the prerequisites?
You need Node 24+ because the plugin uses `node:sqlite`. No API key is required by default — all processing runs locally.
How does dsh-mneme connect to DeepSeek Harness?
It installs into the DSH `web` profile as a bundle plugin; during chats the AI automatically records key info and injects relevant memories into new sessions.
How is it different from pasting context each session?
dsh-mneme persists memories as local Markdown files and auto-consolidates them in the background, so the AI remembers projects, preferences, and decisions across sessions instead of starting fresh.
Is my memory data sent anywhere?
No. The README states data stays on your machine, memories are local Markdown files, there is zero network dependency by default, and no telemetry or remote logging.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
webnovel-writer
by lingfengqaq
A long-form Chinese web-novel writing assistant for Claude Code and DeepSeek Harness, designed to reduce memory loss and hallucinations in serialized projects of up to 2 million characters.
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
08Data and sources
dsh-mneme gives DeepSeek Harness cross-session memory.
All memories stored as local Markdown files, human-readable and editable
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-30. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.