DSH Marketplace

dsh-mneme

slow-stack/dsh-mneme#dsh-mneme

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

24226JavaScriptMITSource

Install

Add dsh-mneme to DeepSeek Harness

Install into

via npm

Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run yesterdayon DeepSeek Harness 0.2.2-rc.5.

Show it in your README

install verified — dshmarketplace

For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.

Due diligence

Before you install dsh-mneme

  • Source of record: slow-stack/dsh-mneme — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.

Security

What installing dsh-mneme runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.5, yesterday.

Install hooks

package.json declares no preinstall, install or postinstall script.

Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.

README mentions

shell commands (bash, exec, spawn …)

Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.

Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.

The AI take

What it is — dsh-mneme is a cross-session memory plugin that recalls across sessions, auto-consolidates memories, freezes conflicting memories for review, and keeps a replayable audit trail with local semantic search over SQLite.

Who it is for — When using DeepSeek Harness for multi-agent projects that require cross-session agent isolation and preference retention with local semantic search. If operating only within a single session without needing isolation or audit features.

Watch out — Sandbox test passed in a fresh profile with successful registration. Static check indicates execution of shell commands. No obvious pitfalls found.

The verdict — I would install it because of the cross-session memory and agent isolation, but only if shell command execution is allowed in the environment and memory deletion is not required.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What dsh-mneme does

Conversation fragments become local memory, are consolidated, and flow back through retrieval into a session.

dsh-mneme is a DeepSeek Harness plugin that provides cross-session memory stored on the local machine. DeepSeek Harness distils useful facts, preferences and decisions when a conversation ends, then injects relevant memories into later sessions. The data lives in SQLite under ~/.mneme/memory, alongside ten human-editable Markdown mirrors. Local semantic search uses an embedding model and runtime cache under ~/.mneme/{models,runtime}.

While idle, autoDream consolidates memories by merging duplicates, compressing stale content and archiving old items. Conflicting memories are frozen for review rather than resolved automatically. Each memory retains provenance and change information; consolidation records input snapshots, decisions and result hashes for replay. A settings panel supports browsing, filtering, searching, editing and deletion, while an entity graph exposes relationships. The plugin also provides the mneme-memory MCP server, the dsh-mneme-serve daemon and an HTTP API for other clients or plugins.

dsh-mneme is intended for developers who want persistent project context, preferences and decisions without sending the memory store to a Mneme service. It is a poor fit where cross-session memory is unnecessary, or where Node 24+ and DeepSeek Harness 0.1.x or 0.2.x cannot be used. Local semantic search can be offline; autoDream and autoSummarize use the configured host model unless their providers and models are cleared or the features are disabled. The terminal surface reaches the agent's environment through the CLI and daemon commands, which can read and modify the configured memory store.

dsh-mneme documentation

How dsh-mneme works

DeepSeek Harness loads dsh-mneme as a memory plugin. At the end of a conversation, the plugin distils selected content into atomic memories and stores them in SQLite, then mirrors them to Markdown files. Later retrieval combines semantic search with recency, importance and usage heat before injecting results into the session context. Hand-edited Markdown takes precedence when merged back into the database.

During idle periods, autoDream consolidates duplicate or stale memories and archives older material. autoSummarize can summarise content. Both use the host model by default. The plugin freezes conflicting memories for review and records provenance, edits, input snapshots, decisions and result hashes.

Configuring dsh-mneme

The README names these configuration keys:

Key Behaviour
dreamProvider and dreamModel Select the provider and model used for dreaming; configured values bypass the host model.
summarizeProvider and summarizeModel Select the provider and model used for summarisation; configured values bypass the host model.
memoryDir Overrides the memory database and Markdown mirror location.

To keep consolidation fully offline, use a local host model and clear both provider/model pairs, or disable autoDream and autoSummarize. The MNEME_MEMORY_DIR environment variable can also select a custom memory directory.

Commands and integrations

DeepSeek Harness starts the web interface with dsh web; its settings page contains the memory panel. dsh-mneme-serve runs a standalone daemon so scripts, web clients and custom panels can access the same store. The mneme-memory package provides a zero-dependency stdio MCP server with six memory tools. An HTTP API is available for other plugins.

Requirements and storage

DeepSeek Harness must be version 0.1.x or 0.2.x. dsh-mneme requires Node 24+ because it uses node:sqlite. The default database is ~/.mneme/memory; previous ~/.dsh/memory and ~/.dsh/mneme locations remain readable. Connection settings for the CLI and MCP server are kept in ~/.dsh-mneme. Removing the plugin does not remove these files or any custom store.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-mneme

coding-agents

vectorize-io

53k

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython28d ago

AI review

coding-agents

What it is — Hindsight provides long-term project memory management for coding agents.

Who it is for — Developers using AI coding assistants such as Claude Code for code development should install it. If you use a non-Python language for the agent, you can choose other implementations.

Watch out — The plugin requires an API key or token and will execute shell commands. Sandbox testing has not been performed. No obvious pitfalls found.

The verdict — Without sandbox testing results, I would not install it.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Details
41k

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Installed cleanly when we ran it

npm packagePython28d ago

AI review

dsh-memory-plugin

What it is — Connects DeepSeek Harness to an OpenViking server for pre-step recall, profile injection, session capture, viking:// URI guarding, and memory read/write tools.

Who it is for — You keep revisiting the same repo in DeepSeek Harness and lose conventions across sessions, with OpenViking as the place those should live. If in-repo docs and rule files already are your context, or you only open throwaway chats, skip it.

Watch out — It installed on a fresh profile and the harness registered it. A reachable OpenViking server is required, and it executes shell commands.

The verdict — I'll turn it on: the product for me is recall happening before the step, not two more tools the agent might ignore.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details
12k

Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScript25d ago

AI review

memos-local-plugin

What it is — Hooks DeepSeek Harness to on-device MemOS memory so a turn can be captured, recalled around the next task, queried with memos_* tools, and inspected in a viewer.

Who it is for — You keep driving the same repo inside DeepSeek Harness and each new agent turn starts blind because prior decisions are not stored. If memory has to live in a shared team store rather than on your machine, this plugin is the wrong place for it.

Watch out — There is no published package; you wire it up from a subdirectory of the MemOS repo. You must supply an API key or token, and it executes shell commands.

The verdict — The subdirectory tax only pays off if DSH is already where the work happens—I would not install this as a memory experiment.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source

typescript

agentscope-ai

3.8k

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython4d ago

AI review

typescript

What it is — The plugin integrates DeepSeek Harness with ReMe's knowledge base to automatically capture main-agent conversations as user Markdown memory and schedule consolidation.

Who it is for — When managing main-agent conversations with DeepSeek Harness and wanting to capture completed dialogues as user-owned Markdown memory, this plugin provides integration. For users who do not want to share the workspace with ReMe, independent knowledge base tools offer a different perspective.

Watch out — The plugin requires manually allowing the build script when installing from source. Sandbox testing has not been completed. The plugin executes shell commands.

The verdict — If I am willing to manually allow the build script from source, I would install it because it connects conversations to persistent Markdown memory.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

ReMe

agentscope-ai

3.8k

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython16d ago

AI review

ReMe

What it is — Integrates ReMe's local-first self-evolving personal knowledge base with DeepSeek Harness.

Who it is for — When running agents using DeepSeek Harness that require automatic capture of conversations as Markdown memory, this is suitable. If you do not need shared local workspace across agents, you can skip this plugin.

Watch out — No obvious pitfalls found. The plugin will execute shell commands.

The verdict — I would install it, but only if shell command execution is permitted.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

MemSearch

zilliztech

2.9k

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython7d ago

AI review

MemSearch

What it is — MemSearch provides shared Markdown memory for DeepSeek Harness coding agents. It supports automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

Who it is for — When building complex coding agents with DeepSeek Harness that require persistent context across sessions, MemSearch offers value. If your work involves only short-lived conversations without cross-platform memory needs, you can skip it.

Watch out — It will execute shell commands. Sandbox testing has not been done yet; no obvious issues were identified.

The verdict — I would install it because it enables memory to evolve into reusable skills, but only if you are willing to use it via subdirectory installation and accept shell command execution as a trade-off.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source