unified-agent-memory
Run the following command in DeepSeek Harness:
dsh plugin install Noelune/unified-agent-memory
Paste the following prompt into your AI chat to install this plugin:
To install the unified-agent-memory plugin in DeepSeek Harness, run the command 'dsh plugin install Noelune/unified-agent-memory'. The full source code is available at https://github.com/Noelune/unified-agent-memory.
About this plugin
Traditional multi-agent systems often suffer from fragmented memory, where agent states are siloed and incompatible across runtimes. unified-agent-memory addresses this by providing a unified memory layer built on Obsidian Vault standards, enabling disparate agents like dsh, Codex, and Claude Code to share a single knowledge base for cross-fleet synchronization and auditing. Its core strength lies in offering a full lifecycle management pipeline—covering ingestion, promotion, conflict adjudication, and decay/retention—all powered by a pure Python standard library engine with SQLite FTS5 local indexing, ensuring zero external dependencies. Security is enhanced through prompt isolation and automatic credential redaction. This plugin is ideal for developers building multi-agent collaborative systems who need visualizable, maintainable long-term memory, as well as AI architects prioritizing data privacy and local-first storage solutions.
Use Cases
- Multi-agent fleets sharing a unified knowledge base for state synchronization
- Visualizing and auditing agent-knowledge with Obsidian for manual review
- Local storage and search to ensure data privacy and high performance
Best For
- AI developers building multi-agent collaborative systems
- Architects needing unified memory management and knowledge visualization
- Technical teams prioritizing data privacy and local-first storage
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.