dsh-trivium
Run the following command in DeepSeek Harness:
dsh plugin install QWQcool/dsh-trivium
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, please run the command dsh plugin install QWQcool/dsh-trivium to install, with source code at https://github.com/QWQcool/dsh-trivium.
About this plugin
DeepSeek Harness users often face the challenge of losing context between conversations. dsh-trivium solves this by introducing an in-process graph memory kernel, offering persistent storage without extra servers. It abstracts memory into nodes and edges, enabling cross-session retrieval and relationships. By default, it stays "quiet," injecting information only when needed, while optional "Chips" allow users to pin critical data for flexible management, ensuring AI assistants remain coherent in complex tasks. This plugin is designed for developers seeking long-term contextual memory, helping AI retain decisions and preferences without adding system overhead.
Screenshots
Use Cases
- Letting AI remember key decisions and project status in long-term development.
- Retrieving historical errors and fixes across sessions when debugging complex apps.
- Managing specific knowledge bases, letting AI remember user preferences and business constraints.
Best For
- Software developers needing long-term contextual memory.
- Users building complex agents with DeepSeek Harness.
- Architects looking to optimize AI context management and retrieval efficiency.
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.