dsh-engram
Minimalist token-saving long-term memory plugin for DeepSeek Harness with zero-LLM capture and ESR evidence closure.
Install
$ - **安装方式已验证 / Verified install**: dsh plugin --profile web add dsh-engramPlugin 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.
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.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
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
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Long-term spatiotemporal memory, zero-LLM whitebox reasoning, and knowledge flywheel integration for DeepSeek Harness via AEIS.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →