← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-lan-memory

Local-first memory and persona plugin for DeepSeek Harness using file storage, BM25 recall, and persona status cards.

UI & ProductivityTerminal & TUIDeveloper ToolsBrowser & WebSkills & Workflows
1GitHub Stars0ForksUpdated2026-10-22

Install

$ dsh plugin --profile desktop add "C:\path\to\dsh-lan-memory"

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-lan-memory is a local-first memory and persona plugin built for DeepSeek Harness (DSH). It provides persistent, human-readable file storage across three distinct memory tiers alongside an auto-compiled profile, zero-LLM session capture, BM25 retrieval, and a customizable SOUL/MOOD persona layer with interactive mood cards and a local web management panel.

Key Capabilities

  • Three-tier file memory architecture using pinned Markdown, BM25-searchable JSONL, and experience logs
  • Automated memory profile compilation extracting atomic facts using configured DSH models
  • SOUL/MOOD persona system with themed mood status cards rendered directly in the conversation UI
  • Built-in agent tools including lan_remember, lan_recall, lan_list, lan_forget, lan_organize, and lan_status
  • Zero-LLM session capture recording local journals with automatic mechanical deduplication
  • Embedded local web management dashboard and native DSH Desktop settings panel integration
  • Data integrity protections including atomic writes, single-writer locking, snapshots, and undo capabilities

Useful For

  • Providing durable long-term memory across sessions without external vector databases or third-party APIs
  • Enforcing consistent conversational personas, mood states, and tone rules for DeepSeek Harness agents
  • Auditing, manually inspecting, and editing agent memories directly in human-readable Markdown and JSONL files

Who It Fits

  • DeepSeek Harness Desktop users needing persistent multi-session memory
  • Developers seeking fully local, inspectable memory stores without external vector DB dependencies
  • Agent builders crafting customized persona and mood behaviors

Documented Limitations

  • Requires DSH Desktop 0.2.1-rc.2 or compatible 0.2.x environment with Web GUI support (webServer service)
  • Headless and TUI profiles are unsupported and will not load the plugin or its tools
  • Installation requires Desktop app to be fully shut down when adding via CLI

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
kiefeng/dsh-lan-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
34890ae · 2026-10-22

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
1GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-22
Last release
2026-10-22
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app