Install
No clear install command was found in the current repository evidence.
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.
Key Capabilities
- Pre-response memory injection using tiered retrieval without relying on manual user recall prompts
- Three-layer local markdown memory hierarchy encompassing user rules, workspace notes, and append-only daily logs
- Multi-tier retrieval engine supporting zero-dep lexical BM25, built-in Transformers.js embeddings, or an optional Python BGE-M3 sidecar
- Astra-style handoff ledgers and whiteboard continuity when token limits approach threshold
- External session and memory scanning from tools such as Claude Code, Codex, and WorkBuddy
- Full-featured browser workbench panel with calendar scheduling, audit ledger, and workspace mind maps
Useful For
- Preserving critical technical decisions and context across long-running or multi-window coding sessions
- Injecting cross-project user preferences and coding guidelines automatically into every conversation turn
- Reviewing and auditing agent memory activations through structured evidence trails and scoring tabs
- Migrating and unifying local memory traces left by various AI coding assistants into DeepSeek Harness
Who It Fits
- DeepSeek Harness developers working on multi-day or complex software engineering projects
- Users running local or offline models who require local-first, privacy-respecting memory persistence
- Power users managing extensive cross-workspace contexts and workflow guidelines
Documented Limitations
- Whiteboard content is currently injected into turn guidance but not yet indexed for memory_recall search
- Advanced BGE-M3 semantic retrieval requires an optional Python sidecar and additional disk space
- Built-in JS semantic tier requires native dependencies (@huggingface/transformers and onnxruntime-node)
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.
package.json declares 0 runtime, 0 development, 1 peer, and 1 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as BSD-3-Clause.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Aik358/dsh-auto-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 9478261 · 2026-10-17
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
- 129GitHub stars
- Forks
- 10
- Open issues
- 1
- Last commit
- 2026-10-15
- Last release
- 2026-10-14
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.
View plugin →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →