Plugins

DSH knowledge-base plugin and Windows desktop client sharing original-file indexing, classification, retrieval and compatible library services. 插件 2.5.5 / 客户端 1.1.2。

Personal cross-session memory in local SQLite, with automatic conversation learning, companion states, and optional semantic retrieval. Currently intended for single-user local use on Windows.

Local literature knowledge-base RAG for DSH: hybrid BM25 + vector retrieval, cross-encoder reranking, cited answers with section- and page-level provenance, metadata-only refresh and background ingest with progress polling, over a SQLite index.

DSH-native integration layer for the Minta memory engine: composes the official dsh-mcp-client row, registers the minta-memory-governance skill plus a session-start memory prewarm, and ships a Minta agent preset; requires the separately deployed Minta engine (Python/Docker) to provide the 19 MCP tools - not usable without it.

A web-novel writing engine for DeepSeek Harness: parallel drafting, outlining and brainstorming with a separate DeepSeek key, lore and foreshadowing management, semantic vector retrieval, a corpus library, usage ledger, mechanical proofreading, and a local serialization plan.

Native side-by-side chat beside the main conversation: an independent DSH session with native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

Connect DeepSeek Harness to 3Chat via OAuth for customer and conversation search, context retrieval, confirmed messaging, and batch-send tracking.

Static codebase analysis for onboarding: scans a project, builds a dependency graph, and writes evidence-cited architecture, module, key-flow and getting-started docs, plus project-level Q&A over a local retrieval index (no network or LLM by default; LLM narrative is optional and off unless enabled).

Read-only semantic retrieval for meow-memory: a local bge-m3 vector index over memory entries and conversation turns, a knowledge graph, and verbatim turn recall. Never writes back to the memory store; requires meow-memory.

Standalone Network Engineer Assistant agent preset plus a bundled 32-doc command knowledge base skill for DPtech, H3C, Huawei and Ruijie switches and routers: KB-first retrieval, cross-vendor command translation, topology and CLI-output screenshot reading, online manual lookup with cited sources, and mandatory risk annotations for dangerous commands; answers networking topics only.

Literature research toolset registering 26 model tools over PubMed, Europe PMC, OpenAlex, PubTator3 and Semantic Scholar: field-syntax search, ID conversion, bibliographic lookup, citation formatting, MeSH and related-article walking, PubTator bioconcept resolution and relation queries, Europe PMC and Semantic Scholar paging, full-text retrieval, and open-access PDF discovery with optional download. A unified search deduplicates hits across sources and orders results by cross-source hits, then relevance, then citation count; a session knowledge graph with PubTator concept enrichment commits to a persistent user graph and renders as Mermaid. Most sources need no key.

A Cyrene-themed agent for DSH, with a customizable look (palette, wallpaper, particle effects, background music, typing sound) and a code security scan. It carries a worldbook, long-term memory and a speech-style correction layer (every reader gets their own Cyrene), plus retrieval over the script to back up its answers.

Turns a local Obsidian vault into a dedicated RAG chat panel: a sidebar page with the note browser, the retrieval-augmented chat and the cited source side by side, answering from fully local BM25 plus CJK-bigram retrieval over your notes and streaming through the DSH model channel, with clickable \[n] citations and mtime-based incremental indexing.

Connect a DSH Agent to Minecraft Java servers with Mineflayer, a live game view alongside native reasoning and tools, configurable personas, server-scoped notebooks, and optional local survival knowledge retrieval. Reuses the host model; installation does not connect to a game or start inference.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Local long-term memory for DSH sessions: archives older turns under context pressure, with a turn-summary index for faster turn lists, statistics, window probing and archive planning (rebuilt automatically when unavailable, with a manual full verification), four tiered hot-memory boards, project documents with enabled/disabled/archived filters and optional owner-controlled family sharing, project hot memory, dual user/assistant turn previews, memory families with editable names and root transfer, root-abdication recovery, orphan-family takeover, summary keyword locator with segment-level candidates and paging, manual injection, 20K segmented reads, and tag-related retrieval. Includes staged recall cues, automatic compatibility with older memory layouts, and post-install version verification. Off in each new session until you turn it on with `/palace on` or the Memory Palace tab. All data stays in the workspace.

Local-first experience library for DeepSeek Harness: error-signature retrieval, pre-step recall hints, failure-to-fix drafts, gap-to-entry closure, and a full-page library view. Ships a sanitized starter library. No model calls, no network.

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Built-in Obsidian-style knowledge base for DSH: agents distill conversations, documents and web sources into a structured .wiki graph, with retrieval, graph export, note editing, incremental builds and multi-vault management.

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Dual knowledge-graph RAG for Markdown notes with half-life memory decay: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight-feedback loop — a native Cordis plugin, npm-installable as @eqman00003/knowlp-rag.

Reversible context folding plus external memory for DeepSeek Harness: tool output collapses into expandable lines, session facts become auditable records.

QQ-bot console for DeepSeek Harness on Windows, with NapCat/AstrBot deployment, GPT-SoVITS integration, persona editing, local hybrid memory retrieval and a 3D memory graph. The services do not start automatically, and strangers get no tool access by default. QQ messages reach DSH through the third-party AstrBot (astrbot_plugin_dsh) and dsh-astrbot-ingress, both deployed from pinned sources.

Five-layer intent recognition pipeline (rules, pgvector retrieval, Jev scoring, fine-tuned arbitration, LLM fallback) with scenario management UI, PostgreSQL storage and distributable API services.