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 Market. Browse, search and one-click install human-curated community plugins without leaving the app, synced daily with dsh-plugin.org.
Graph Memory is a native knowledge-graph memory plugin for DeepSeek Harness, extracting structured triples from conversations, compressing context by ~75%, and enabling cross-session experience reuse with traceable recall.
Mnemon provides LLM-supervised persistent memory for DeepSeek Harness, with graph-based cross-session recall in a single binary, zero API keys, so AI agents never forget.
billion-context is a universal context-compression proxy for AI coding agents; mounted as a DSH plugin it folds consumed conversation into layered summaries so one session can push billions of tokens without blowing the context window.
dsh-memory equips DeepSeek Harness with AGI-grade persistent memory, enabling cross-session coherence, white-box intelligence, and auditable trust for a self that never forgets.
Engramory is a portable memory protocol for DeepSeek Harness, using zero-infrastructure Markdown files and an index for long-term memory, loaded as standing rules with a validator.
dsh-memory is a local Git-backed long-term memory plugin for DeepSeek Harness, storing memory safely in a local repository with settings UI, retrieval, and recovery.
A cross-session memory plugin for DeepSeek Harness with a seven-layer SQLite store (soul/user/project/fact/lesson/topic/rules), BM25 retrieval, and per-window dream consolidation.
Cross-session memory plugin for DeepSeek Harness: seven-layer SQLite store, BM25 retrieval, and per-window dream consolidation to help AI remember users and projects.
DSH Noema provides durable, inspectable long-term memory for DeepSeek Harness, with recall tools and a settings page for cross-session knowledge retention.
A DSH plugin with three-layer auto memory: per-turn consolidation, smart retrieval, proactive calendar reminders, warm greetings, and inheritance of memories from other AI tools.
dsh-evolve-in-git is a DeepSeek Harness plugin that uses a Git repository as long-term memory, auto-committing session notes, branch records, and skill drafts for agent evolution.
YOLO is a personal assistant plugin for DeepSeek Harness that automatically extracts todos, goals, and milestones from conversations, saves them across sessions, tracks changes, and reminds you on time.
A DSH plugin that gives coding agents a second brain: seal and distill daily into Obsidian, hit the exact page tomorrow for persistent memory and self-evolution.
Local-first cross-session project memory for DeepSeek Harness: JSON SSOT + PROJECT_MEMORY.md, bounded Hot Memory, BM25 retrieval, lifecycle and provenance, no embeddings or external services.
Oh My DSH is an all-in-one enhancement plugin for DeepSeek Harness, bundling long-context compaction, task and verification reminders, prompt optimization, CodeGraph code understanding, OpenCU computer control, and four complete themes.
Adds cross-session long-term memory to DeepSeek Harness: auto-distills layered memories (L0-L3) and injects them into context, keeping personal and work memories separate, zero-config.
A DSH plugin providing persistent project memory for DeepSeek Harness, indexing documents and code symbols with auto-refresh and cited recall, featuring BM25 retrieval and experience notes.
An instant, near-lossless context compaction engine for DSH plugin, compressing in milliseconds with zero model calls, keeping original tokens, and shipping recall/search tools for lossless read-back.
A DSH plugin bringing OpenViking semantic retrieval, resource management, and auto-recall with user/agent dual-space memory and session auto-commit to DeepSeek Harness.
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
Related Terms
- Memory & Context DSH Plugin
- A Memory & Context DSH Plugin manages DeepSeek Harness' long-term memory — cross-session memory, auto-summarization, context compression and vector recall — remembering what matters and forgetting the rest.— DeepSeek Harness architecture docs
- Cross-session memory
- Cross-session memory is a memory plugin's persistence of information across conversations — preferences, facts and conclusions carried into new sessions without restating.— DeepSeek Harness architecture docs
- Context compression
- Context compression is a memory plugin's summarization of history beyond the window — keeping key facts, trimming redundancy, avoiding truncation in long sessions.— DeepSeek Harness architecture docs
- Vector recall
- Vector recall is a memory plugin's embedding of memories for semantic retrieval — a question surfaces relevant history instead of exact keyword matches.— DeepSeek Harness architecture docs