DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-engram

Minimalist token-saving long-term memory plugin for DeepSeek Harness with zero-LLM capture and ESR evidence closure.

UI & ProductivityTerminal & TUIDeveloper ToolsBrowser & WebSecurity & PolicySkills & Workflows
6GitHub Stars1ForksUpdated2026-09-14

Install

$ - **安装方式已验证 / Verified install**: dsh plugin --profile web add dsh-engram

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-engram is a minimalist, token-conscious long-term memory plugin for DeepSeek Harness. It features zero-LLM pattern-based auto-capture, secret redaction, a bounded symbolic [ENGRAM] index designed for KV-cache stability, and an ESR-lite evidence closure protocol that enforces artifact verification before task completion. It also introduces Context GC to replace lossy summaries with mechanical pointer re-fetching, alongside a comprehensive native web viewer featuring Kanban boards, relation graphs, and observability telemetry.

Key Capabilities

  • Zero-LLM auto-capture of git milestones, key file edits, and tool errors with automated secret redaction
  • Bounded symbolic index block frozen per session to maximize prompt KV-cache reuse
  • Evidence-driven ESR task lifecycle (draft, active, stable) requiring verifiable proof before closure
  • Context GC compaction engine replacing lossy LLM summarization with mechanical pointer summaries
  • Native DSH settings integration including ESR Kanban board, force-directed SVG relation graphs, and usage telemetry

Useful For

  • Maintaining token-efficient cross-session context and knowledge retention across complex agent workflows
  • Enforcing strict evidence requirements (artifacts, evaluations) for multi-step task completion
  • Optimizing agent context compaction by swapping lossy LLM summaries for precise retrieval pointers

Who It Fits

  • DeepSeek Harness developers seeking token-efficient memory architectures
  • Agent engineers managing multi-turn, multi-session autonomous development tasks
  • DSH users who need transparent task tracking and relation graphs within the native Web UI

Documented Limitations

  • Requires Node.js runtime version 22.19.0 or higher
  • Preset-plane auto-compaction requires presets with standard Cordis layouts
  • Symlinked local development installs require running manual dependency link setup scripts

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.

No automated security signals have been published yet.

Source & Registry Notes

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

Source repository
skepsun/dsh-engram
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
e1696a1 · 2026-09-16

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
6GitHub stars
Forks
1
Open issues
4
Last commit
2026-09-14
Last release
2026-09-14
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