Plugins

Trusted office suite for government/enterprise work by Beijing Caizhi Technology (深知可信智能): three skills — trusted consulting (policy/regulation Q&A with citation markers + provenance HTML), trusted search (authoritative policy/standard retrieval with traceable HTML + clean Markdown), and official-document writing (draft/rewrite/Word/red-head delivery); all interfaces go through the dknowc trusted workbench MCP (Bearer auth), products land in the session workspace, one-time key setup persists for later sessions; ships on npm as dknowc-dsh.

Thin on-demand context retrieval: context_query / context_slice / context_grep tools that read already-persisted history back with replay-safe citations.

Cross-session memory for DeepSeek Harness: three-way recall (BM25, dense vectors, and Personalized PageRank over a memory graph) fused with RRF, emotion as a modulation multiplier, power-law forgetting with five sinking layers, and an interactive memory star map. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

Research-style problem solving in four gated stages: record sources by retrieval tier with local before web, turn each shortfall of existing tools into a gap that needs evidence, score candidates against weighted metrics with a deterministic engine, fuse or improve the weak ones, then iterate on measured deltas. Also organizes a directory into human-facing and machine-facing trees.

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

Socratic tutor tools for DSH: cited retrieval, page images, chapter index, session review, embedded console. Teaching behaviour lives in dsh-socratic-persona.

Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and checked against a 112,175-line game-dialogue corpus) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also a skills library and a sticker library (you import your own images; none are bundled) that sends a fitting sticker at the right moment. On by default: a text bubble with her avatar after each reply, which costs one extra small model request unless the agent already announced (voice.bubble: false turns it off). Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).

Cross-session long-term memory for DSH: eight memory layers, four notebooks, hybrid SQLite FTS5/vector/graph retrieval, agent-driven automatic capture, write lifecycle hooks, optional write audit, project spaces, forgetting and a visual management page. Full FTS5/vector/graph retrieval needs the bundled Go service, which ships only as a Windows x64 prebuilt; on macOS/Linux, build it from source or the plugin falls back to Node SQLite without FTS5 and retrieval degrades.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.

Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.

A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).

Memory for DeepSeek Harness with five sections (memories, tree, profile, graph, inbox), a rule-based capture policy that decides what to keep and what to drop, and hybrid BM25 plus vector retrieval over parent and child chunks, backed by twelve agent tools that read and write the same local files.

Character-chat memory layer that keeps persona, voice and relationship state separate from summaries, archives every raw message for retrieval, and ships a SillyTavern card importer plus an OpenAI-compatible gateway.

StartLux Decision: a cheap judgement layer for DeepSeek Harness — all nine decision points (tool authorization, model routing, delegation, compaction, turn continuation, retrieval, skill pick, session title, COT translation) are implemented and individual

Network Engineer Assistant preset plus a 12-vendor, 96-document switch/router/firewall command knowledge base skill (Huawei, H3C, Ruijie, DPtech, Cisco IOS/IOS-XE, Cisco NX-OS, Juniper Junos, Arista EOS, Fortinet FortiOS, ZTE ZXR10, VyOS, MikroTik RouterOS) with KB-first retrieval, cross-vendor command translation, topology and CLI screenshot reading, cited online manual lookup, and mandatory risk annotations for dangerous commands; answers networking topics only. A community continuation of sososilencing/dsh-network-engineer (see NOTICE.md); it cannot be installed alongside that upstream plugin because both register the network-command-kb skill and a 网络工程师助手 preset.

Reads the local NTQQ (QQ 9.9.x) message database on Windows and Linux and exports group and private chat history to txt, csv, json, md, html or sqlite. Ships sixteen model tools: qqnt_status and qqnt_doctor for environment and blocker checks, qqnt_extract_key, qqnt_index to build or inspect the sidecar index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats for totals and monthly counts, qqnt_export_group, qqnt_export_chat and qqnt_export_batch (a chat can be named the way the user says it, and ambiguity refuses instead of guessing), qqnt_jobs for OCR, speech-to-text, chunking and model downloads, qqnt_media for a chat's downloaded images, qqnt_storage for disk usage and allow-listed cleanup, and qqnt_ask plus qqnt_recall for retrieval with citations. The local web UI on 127.0.0.1:46728 adds an incremental SQLite index, six views (chats, export, statistics, ask, settings, models), a task panel, a single-pane layout on narrow screens, sender redaction, media bundling, per-day splitting, export presets and AES-256 password ZIPs; OCR, speech and embedding components install into the plugin's own virtualenv on demand. Needs python3 with sqlcipher3 (the settings page can create a private virtualenv), and the database key is read from the running, logged-in QQ client.

DSH-elysia — shared Markdown memory for every DSH session: persona, requirements, corrections, lessons, methods, requests, sessions, a method library and ingested documents, mirrored to a second disk with version snapshots and a cross-process write lock; entries move between the main file and a searchable archive by hit frequency and repeated emphasis, and retrieval is keyword co-occurrence plus BM25. Ships a skills library (SKILL.md playbooks with optional guarded run.mjs execution), a sticker library that sends a fitting sticker at the right moment, and — new in 1.10 — Memory Packs: a bundled, opt-in character memory (packs/elysia: 61,903-char identity + 2,482-char persona distilled from 1,696 official voice lines and 112,175 dialogue lines). Packs are off by default, back up before writing, only touch identity/persona, and can be uninstalled to restore what was there.

Five native tools for Social Data discovery, pricing previews, approved reads, stored-result retrieval and source tables; requires a BeatAPI key for paid reads.

Persistent persona memory for DSH with a unified recent, long-term and archive timeline, bounded context loading, memory retrieval and isolated task delegation.

Token-efficient web reading for DeepSeek Harness: one call fetches several pages through a real Chrome/Edge over CDP, gates them by relevance and returns a single digest, cutting context tokens by 80-98%. Real search URLs, login flow, screenshots, three proxy modes.

Bundles the kb-curator skill, which keeps a local three-layer knowledge base and refuses to index anything the user has not approved. The L2 retrieval layer needs @kenz1117/dsh-engram installed separately, and the engine runs on Windows only.

Semantic workspace search: three model tools (`zg_search`, `zg_index`, `zg_status`) drive the `zg` CLI for hybrid BM25 + vector + RRF retrieval, with a search-first guard that makes `grep`/`rg` require a prior successful search in an indexed workspace.

Code retrieval engine exposed as an MCP server: four tools (code_search, code_outline, code_index, index_status) over a SQLite FTS5 index with BM25 ranking, CJK bigram indexing, declaration-aware tree-sitter chunking, incremental reindexing, and a three-layer secret filter. The bigram index matches Chinese-language queries against English code, and the default path needs no vector store or embedding model. Requires a local Python 3.10-3.12 engine installed by scripts/install.sh, and CODERAG_ROOT set in the profile patch.