dsh-patchouli
Run the following command in DeepSeek Harness:
dsh plugin install memorax-ai/dsh-patchouli
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install memorax-ai/dsh-patchouli in your DeepSeek Harness terminal to install this plugin; the full source code is available at https://github.com/memorax-ai/dsh-patchouli .
About this plugin
In multi-agent DeepSeek Harness environments, memory and knowledge data are scattered across plugins with fragmented retrieval pipelines, leaving developers without a unified entry point for heterogeneous data augmentation. Patchouli exposes a single update / retrieve / subscribe service inside Harness, fully decoupling the data layer from algorithmic plugins while a harness-neutral Rust transactional backend guarantees durable, reliable storage. Core capabilities include a common memory service with provider filters, user routing policies, and provenance tracking; incremental retrieval streams with backpressure that conclude with a complete aggregate; a built-in Agent Loop connector with configurable hooks and model tools; pluggable local or remote memory and knowledge implementations; typed image and workspace-file ingestion as Artifacts; and compatibility with external memory plugins such as MemoraX, OpenViking, and Engramory. It is ideal for teams building multi-agent systems that need a single automatic recall path across multiple memory plugins, or for developers who want to adapt existing plugin versions without maintaining an upstream fork.
Screenshots
Use Cases
- Unifying recall across multiple memory plugins in a multi-agent setup
- Plugging a swappable local or remote memory backend into the Agent Loop
- Adapting several memory plugins across versions without maintaining an upstream fork
Best For
- Developers building multi-agent collaboration systems
- Teams needing local persistent memory and knowledge management
- Engineers integrating multiple memory plugins behind a unified interface
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.