← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-trilogy

Per-project Markdown memory management plugin for DeepSeek Harness with automated scaffolding, context injection, and web UI.

UI & ProductivityDeveloper Tools
2GitHub Stars0ForksUpdated2026-09-28

Install

$ dsh plugin --profile web add link:D:/path/to/dsh-trilogy

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-trilogy is a host-level project memory plugin for DeepSeek Harness. It automatically provisions and maintains three structured Markdown memory files (PROJECT.md, DECISIONS.md, and SESSIONS.md) per workspace, automatically injects relevant context into new sessions without reliance on vector databases or embeddings, and provides a web-based management UI with zero-dependency BM25 search.

Key Capabilities

  • Automatic scaffolding and session startup injection of PROJECT.md, DECISIONS.md, and SESSIONS.md
  • Provides memory_checkpoint, memory_read, and memory_search (BM25) tool endpoints for DSH models
  • Deferred nudge reminders for capturing significant session actions without breaking dialogue flow
  • Web interface in settings for viewing, archiving, restoring, exporting, and importing memory packs
  • Dynamic budget allocation and multi-area prioritization to keep prompt context injection KV-cache friendly

Useful For

  • Maintaining continuity and architectural decisions across multiple independent DeepSeek Harness sessions
  • Bootstrapping contextual awareness and testing instructions for new or undocumented projects
  • Preventing repetitive mistakes and knowledge loss during ongoing code refactoring

Who It Fits

  • Developers working on long-term or multi-session coding projects in DeepSeek Harness
  • Teams seeking structured, file-backed project documentation managed directly through model workflows

Documented Limitations

  • Does not use vector embeddings or neural semantic search (relies on Markdown parsing and BM25 ranking)
  • Bypasses harness ctx.fs seam in favor of direct node:fs filesystem writes for consistent cross-provider scaffolding
  • Web management endpoints are restricted to local loopback access only

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, 3 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
TodayJin/dsh-trilogy
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
27f47db · 2026-10-15

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
2GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-28
Last release
2026-09-28
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