← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-memory-recall

Persistent memory and past session recall for DeepSeek Harness based on Hermes Agent.

UI & ProductivityTerminal & TUIDeveloper ToolsBrowser & WebSecurity & PolicyRemote Execution
0GitHub Stars0ForksUpdated2026-10-25

Install

$ dsh plugin --profile web add dsh-memory-recall

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-memory-recall brings Hermes Agent-style persistent memory to DeepSeek Harness. It maintains user profiles and model notes across chat sessions in local plain-text markdown files, automatically injecting relevant memory contexts while preserving prompt caching. It also provides an interactive sidebar management panel and a permission-gated session_search tool to query past conversations.

Key Capabilities

  • Stores user profile and model notes persistently in local markdown files
  • Appends memory context to conversations automatically on session start, edits, and compaction
  • Searches previous chats via session_search protected by explicit user approval prompts
  • Provides a sidebar Memory panel to view, edit, delete, and manually add memory entries
  • Groups chats and workspaces under the @ mention trigger menu in the chat input
  • Scans model memory writes for prompt injection and credential exfiltration patterns

Useful For

  • Retaining developer environment facts, preferred coding styles, and project conventions across new sessions
  • Recalling previous technical decisions and discussions from earlier chats without copying transcripts manually
  • Managing and pruning stored AI preferences and agent notes via an interactive visual UI

Who It Fits

  • Developers using DeepSeek Harness who require persistent context across multiple sessions
  • Power users wanting full local control and inspection over model memory and recall logs

Documented Limitations

  • Requires DeepSeek Harness with web profile (dsh 0.1.5 or later) and Node 22+
  • Optimal search performance depends on configuring dsh's optional SQLite full-text index patch (cordis.patch.yml); otherwise it falls back to scanning the last 150 chats
  • Sub-agent sessions do not receive or query persistent memory

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 NOASSERTION.

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
adithyanraj03/dsh-memory-recall
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
c54b1ad · 2026-10-25

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
0GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-25
Last release
2026-10-25
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