dsh-layered-memory
Run the following command in DeepSeek Harness:
dsh plugin install JunNanLYS/dsh-layered-memory
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, execute `dsh plugin install JunNanLYS/dsh-layered-memory` in the terminal, with the full source code available at https://github.com/JunNanLYS/dsh-layered-memory.
About this plugin
In long conversations and complex cross-session workflows, AI Agents often struggle with context loss, leading to repetitive exploration and excessive token consumption. dsh-layered-memory introduces a comprehensive background layered distillation pipeline to DeepSeek Harness. It automatically processes the full chain from L0 raw capture and L1 atomic memories to L2 scene integration and L3 persona distillation. Before each inference step, it seamlessly injects the most relevant memories into the context as synthesized messages, while also empowering the model to actively invoke tools for deeper scene retrieval.
Screenshots
Use Cases
- Continue complex coding or writing tasks across sessions without re-providing background context.
- Let the Agent remember user preferences, workflow conventions, and historical decisions in long conversations.
- Execute long-chain tasks to significantly reduce token costs caused by repetitive model exploration.
Best For
- Power users who rely on AI Agents for complex, cross-session workflows.
- Creators building personalized assistants with long-term memory and persona capabilities.
- Tech enthusiasts focusing on token cost optimization and Agent context enhancement performance.
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.