Wangdefa.Memory
A local-first five-layer memory MCP plugin for DeepSeek Harness agents.
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
- Provides MCP tools for processing messages and saving completed memories.
- Stores memory locally in SQLite and JSON files.
- Uses five layers for cognition, thinking, experience, feature inference, and delivery.
- Performs tag-based retrieval with synonym expansion, time decay, state filtering, and ranked results.
- Supports two-stage memory writing: pending frames followed by completed memory content.
- Supports preference learning, tag evolution, low-weight memory cleanup, and shallow/medium/deep memory injection routes.
Useful For
- Give a personal-assistant agent persistent local memory across conversations.
- Record and retrieve user preferences, such as coding-style preferences.
- Add memory retrieval and completion workflows to a DeepSeek Harness MCP setup.
- Build .NET applications using the Wangdefa memory APIs directly.
Who It Fits
- DeepSeek Harness users who want an MCP-based local memory component.
- Developers building personal assistant agents with .NET.
- Users seeking tag- and feature-driven memory retrieval rather than a vector-first design.
Documented Limitations
- The project is explicitly labeled early stage, with inference logic planned for further optimization.
- DSH use requires .NET 10.0 or later and a configured DEEPSEEK_API_KEY.
- The documented DSH integration runs an MCP server through a configured local dotnet command and path.
- Memory retrieval is based on tags, synonyms, feature statistics, and time decay; the README describes it as a non-vector memory direction.
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
- VinsonWild/Wangdefa.Memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 3a9dd2f · 2026-09-15
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
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-15
- Last release
- 2026-09-15
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Image generation and iterative editing plugin for DeepSeek Harness supporting cloud providers and local ComfyUI.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →Browser automation plugin enabling DeepSeek Harness agents to interact with logged-in browser sessions safely via dedicated Agent Windows.
View plugin →DeepSeek Harness plugin integrating ego-lite Chromium browser with 32 structured automation tools and live interactive screencast panel.
View plugin →