DSH-Plugin | Memory Context for DeepSeek Harness Plugin
Free Memory & Context DSH-Plugin for DeepSeek Harness: browse, search, download, install context compression, vector recall. Verified, traceable sources.
DSH-Plugin Hub is a community plugin marketplace for DeepSeek Harness (DSH plugin), built to the official plugin spec and embedded in Settings → Plugin Center. Browse, search and one-click install 4000+ human-curated community plugins without leaving the app, synced daily with dsh-plugin.org.
Mnemon gives DeepSeek Harness persistent cross-session memory with graph-based intent-aware recall, in a single binary with zero API keys.
Engramory provides a zero-dependency, file-based memory protocol for DeepSeek Harness, using Markdown files for long-term memory.
Local-first, cross-agent persistent memory for DeepSeek Harness with semantic recall and knowledge graph.
DSH Noema provides durable, inspectable long-term memory for DeepSeek Harness with recall tools and a settings page.
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness.
Cross-session memory plugin for DeepSeek Harness with six-layer structured memory and cache-friendly injection.
Cross-session memory plugin for DeepSeek Harness with seven-layer structured memory and automatic injection/retrieval.
Lingshu, a DSH plugin, provides AGI-grade persistent memory for DeepSeek Harness with cross-session self-evolution and auditability.
Auto-memory plugin for DeepSeek Harness: three-layer memory with auto injection, retrieval, daily reflections, and cross-tool memory inheritance.
DSH plugin for persistent memory: auto-distill session insights, inject into future agents, with a visual panel.
DSH plugin connects to a PowerContext server over HTTP for recall, memory, handoff, experience, and skills.
LLM-free near-lossless context compaction for DeepSeek Harness, with instant compile and recall recovery.
Local-first persistent memory for DeepSeek Harness: hot bootstrap, Chinese BM25 cold recall, lease-lock transactional writes, read-only governance.
DSH plugin integrating OpenViking for memory retrieval, resource management, and auto recall.
A DSH plugin for cross-session cueing, injecting context snapshots of nodes from other sessions into the current conversation for the model to read.
DSH plugin that auto-syncs conversation turns to Honcho memory, injecting persistent context and enabling semantic recall.
Per-host personalization for DSH: global custom instructions, local long-term memory, and reply-tone presets injected into every conversation.
A durable memory layer for DeepSeek Harness with startup context, prompt-time recall, and MCP memory tools.
DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.
How to pick a trustworthy Memory & Context DSH plugin
A Memory & Context DSH plugin manages DeepSeek Harness's cross-session state — context compaction, long-term memory, vector recall and persistence, the key to a continuous persona and working memory. It directly drives behavioral consistency, so check storage approach, recall mechanism and compatibility status — and make sure the data stays yours.
- Storage location: confirm whether memory lives locally or in the cloud, whether it is encrypted and exportable — prefer local storage for sensitive context.
- Recall mechanism: plugins use vector search, keyword matching or summary compaction; evaluate recall accuracy and latency for your workload.
- Compatibility status: memory plugins depend on DSH context APIs — prefer verified plugins whose dshTarget matches your version to avoid data-format incompatibilities.
Where Memory & Context sits in the DSH taxonomy
Memory & Context is one of the eleven primary DeepSeek Harness categories, handling cross-session state: context compaction, long-term memory, vector recall and persistence. It underpins Sessions & Messages and Skills & Agents — without a reliable memory layer every conversation starts from scratch. It is the category that gives DSH a continuous persona and working memory.
「Every part of the product is a plugin — including the model adapter, the tool registry, the session log, and the agent loop itself.」
SourcesOfficial site·Architecture docs·Repository