← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

mneme

Offline cross-session memory plugin for DeepSeek Harness with background auto-consolidation (autoDream) and visual memory panel.

UI & ProductivityDeveloper ToolsSkills & Workflows
137GitHub Stars20ForksUpdated2026-10-01

Install

$ dsh plugin --profile web add @modusensus/dsh-mneme

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-mneme adds persistent, cross-session memory management to DeepSeek Harness. Running offline by default with local SQLite and Markdown mirrors, it features background consolidation (autoDream), conflict freezing with human-in-the-loop review, agent and workspace scope isolation, structured entity-relation graph extraction, and an stdio MCP server for connecting other AI clients.

Key Capabilities

  • Cross-session memory persistence across chat restarts
  • Background autoDream consolidation for deduplication, merging, and tiered archiving
  • Human-in-the-loop conflict review queue to freeze and compare contradicting memories
  • Agent and workspace scope isolation with weighted or strict recall filtering
  • Hybrid search combining BM25, semantic vector embeddings, and entity relation graphs
  • Two-way Markdown synchronization and SQLite storage without cloud dependencies
  • Built-in stdio MCP server for external client integration (Claude Code, Cursor, Codex, OpenClaw)

Useful For

  • Retaining user preferences, coding habits, and project architectural decisions across multiple sessions
  • Extracting structured entity-relationship graphs from long-running technical dialogues
  • Isolating operational memories between distinct AI agents and specific workspaces
  • Sharing local memory stores across DSH and external MCP-compatible development tools

Who It Fits

  • Developers looking for persistent local memory in DeepSeek Harness
  • Users running multi-agent or multi-project workflows requiring context isolation
  • Privacy-focused engineers requiring local-first, auditable memory management

Documented Limitations

  • Requires DeepSeek Harness runtime running locally or active API for MCP server bridge
  • Local embedding and graph features require Node.js 22+ runtime
  • Strict scope isolation and advanced entity extraction require manual opt-in in configuration

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.

License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

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
slow-stack/mneme
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
bdf3e62 · 2026-10-01

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
137GitHub stars
Forks
20
Open issues
14
Last commit
2026-10-01
Last release
2026-09-30
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