dsh-memory-connect
Run the following command in DeepSeek Harness:
dsh plugin install Asher-2000/dsh-memory-connect
Paste the following prompt into your AI chat to install this plugin:
To install this plugin, run the command 'dsh plugin install Asher-2000/dsh-memory-connect', with source code available at https://github.com/Asher-2000/dsh-memory-connect.
About this plugin
AI agents often struggle with context loss between sessions, leading to fragmented memory and lack of personalization. The dsh-memory-connect plugin for DeepSeek Harness addresses this by automatically extracting, storing, and recalling memories across sessions, giving agents persistent intelligent memory and a global identity.
Its core capabilities include auto-extracting facts, preferences, and decisions from conversations; cross-session recall via FTS5 keywords and optional semantic embedding; context explosion prevention with token budget management; a global Soul identity for workspace consistency; and smart maintenance through memory decay, consolidation, compression, and a temporal context graph.
This plugin is ideal for developers and users of DeepSeek Harness who need their AI agents to maintain coherent context, personalized identity, and efficient memory management across multiple interactions.
Use Cases
- Maintaining project context and user preferences across multiple sessions
- Automatically extracting key information from conversations to support decisions
- Preventing context window overflow in long conversations
Best For
- DeepSeek Harness developers and users
- AI application builders requiring persistent memory capabilities
- Teams focused on personalized interaction and context coherence
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.