dsh-project-memory
Run the following command in DeepSeek Harness:
dsh plugin install 00080000/dsh-project-memory
Paste the following prompt into your AI chat to install this plugin:
Run the command below to install this plugin in DeepSeek Harness. You can find the source code at the following GitHub repository: https://github.com/00080000/dsh-project-memory
About this plugin
When developing with DeepSeek Harness (dsh), LLMs often struggle with context loss, forcing agents to re-read entire codebases. dsh-project-memory is designed to solve this critical bottleneck. It acts as a persistent "second brain" across sessions by indexing documents, code symbols, and experience notes to disk. It uses hash-based incremental updates to ensure only changed content is processed, and cross-links documents to code via references for quick verification.
Use Cases
- Persistent cross-session development task management
- Solving LLM context loss in complex codebases
- Automatically recording and deduplicating development experience notes
Best For
- Software engineers using DeepSeek Harness
- AI developers needing long-term project maintenance
- Technical teams focused on context continuity
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.