Plugins

CPU, GPU and memory load in the DeepSeek Harness Session header: three compact cells with a percentage and a 2 px bar, coloured at 75 % and 90 %; CPU from os.cpus() deltas, GPU from nvidia-smi (Windows counter fallback).

Read EPUB, PDF, DRM-free MOBI/AZW3 and TXT in the DSH sidebar. WeChat Read style typography with TOC, bookmarks, highlights and progress memory; select any passage to translate it into Chinese; the Ask-the-Book AI answers only from passages retrieved from the open book. Books and progress stay in local IndexedDB. Four themes including an eye-care green paper, and PDF paper follows the theme.

Replaces the sidebar workspace folder picker with a name box (type a name, get a same-named folder and a new workspace), adds a Move to workspace action that clones a session into another workspace and archives the original, and optional per-workspace memory that opens a continuation session after compaction and adds a workspace_memory search tool.

What it does while she sleeps, in one card. Two things: (1) tidy the element memory — merge synonyms only when the model agrees, trim descriptions, prune weak links, propose analogies for the user to confirm, with a backup before every write and a 15%-of-library cap per pass; (2) dream — stitch her own past experiences (plus props from the element memory) into a short 3–6 sentence story, leave one line on her desk as a note labelled "this is a dream, not something that happened". The dream lives in its own file and never enters her memory or her personality prompt. Requires @ssamurias/dsh-fish for her event stream and dsh-memory-brain for the element library; model-approved merges and dreams need a local Ollama model (or a paid API key).

She keeps the questions your chats left unanswered, then goes and looks them up later. A line she asked you that ended in "?" and never got an answer is stored as a hanging question; on a schedule inside a daily window (08:00–23:00, five a day by default; an optional mouse/keyboard-idle gate is off by default) she picks the oldest one, searches the web and Bilibili, reads what is actually readable, distils it into two or three sentences and leaves a note on her desk. Questions about its own plugins are skipped and left for you. Read-only on her events: nothing is written to her memory, her growth is untouched, and dsh-fish needs no patching. Requires the @ssamurias/dsh-fish persona plugin for her event stream and a local Ollama model; a search API key is optional.

Object memory for DSH: each object is broken into fourteen kinds of smallest elements (shape, material, state, part, function...), observed links are stored apart from inferred ones, and analogies stay as questions until the user answers.

Explains Chinese internet memes to an agent: registers a meme_explain tool that returns the meaning, tone, origin and lifecycle of a sticker, which memes can and cannot be combined, occasions to avoid, and both a meme-version and a plain-version reply. Answers come from a local memory store with spacing-effect decay, falling back to a user-configured OpenAI-compatible vision endpoint (BYOK).

Extends the official QQ bot channel (@tencent-connect/dsh-qqbot 0.5.3/0.5.4) in DSH with sticker tools, idle proactive small talk, long-term memory and a Settings → Plugins page. Install is manual: run lib/patch-host.mjs to patch six files in the installed channel (backed up, revertable) and --register it into your profile; you also need a QQ open-platform bot (appId/appSecret) with "receive all messages" enabled by a group admin. The channel access defaults to open (anyone who can message the bot); set access.c2cMode/groupMode to allowlist or disabled before exposing it.

Rui Xi's Memory (dsh-memory-v2) — a local long-term memory plugin for DeepSeek Harness: four memory collections (semantic / conclusion / profile / temporary), per-day scene archives, two-phase consolidation and literal trace. When structured recall finds nothing, it falls back to searching the daily scene archive: time-window first (yesterday / last week / N days ago / dates), then a 2/7/30/180-day tiered sweep, with line-numbered citations. All data stays in the local DSH directory; semantic recall, diagnostic logs and the sensitive debug route are off by default.

Connects DeepSeek Harness to the hosted Renor memory MCP server over Streamable HTTP, using a Renor API key from RENOR_API_KEY, so the model can call Renor's recall and save tools. It is a configuration bundle with no code of its own.

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).

Companion persona preset with persistent memory, presence heartbeat, idle updates, and a delegated helper agent with built-in fetch and CDP web tools.

A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.

Article Review page in DSH's native right sidebar: turns Markdown, Word, PowerPoint and PDF articles into sentence-addressable text, lets you comment on any sentence, and hands the open review to the agent as a composer draft. Six agent tools let the model read every comment, revise the article (in place for Markdown, as a sibling <name>.revised.md for binary formats), resolve the comments, and record recurring wording preferences into a long-term writing-style memory injected into later prompts. Extraction includes a dependency-free DOCX/PPTX reader; PDF text extraction runs locally through the host's Python + pypdf (or poppler's pdftotext) and is unavailable without one of them. No network calls, no telemetry.

DSH 本地记忆插件：自动记忆、遗忘曲线、关键词关联、可检索可编辑，数据留在本机。

Per-Bot memory for Tobs Bots (requires DeepSeek Harness with @botharness/core; it ships off with no Bots listed, and after you list a Bot and set mode to on it works with no other service): a read-only local full-text index of that Bot's own past conversations (Chinese words found inside sentences), memory imported from other AI tools, a status tool, optional auto recall before a step in which a Human speaks, and a service for other plugins. Richer backends can be chosen at install, with a quote first and a daily token cap: a public fact store (memv2-lite), the official Graphiti graph, or both, fed from the Bot's own conversations.

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.

Sync a git-backed memory folder with a peer machine every time DeepSeek Harness starts — no daemon, no cron, no manual pull.

Bridges the shared ~/.agentloom store between DeepSeek Harness and Codex: injects the shared memories and the AGENTS.md entries the context budget truncates into the system prompt, and adds six loom_* tools for status, sync, memory search/list/add and skill listing. Requires the agentloom CLI installed and a one-time agentloom init; the seven-tool MCP bridge in the same repo is a separate package for MCP clients.

A cross-workspace Library for DeepSeek Harness: agents record files, tools, environments, knowledge and work records so any later session can index, search and reuse them.

Zhinao (second brain) for DeepSeek Harness: Markdown-authoritative layered memory (L1 long-term model gated by user confirmation / L2 knowledge with mandatory sources / L3 recent status under daily quotas), a local recall ledger explaining every injection, lifecycle engine with weekly review and a Web panel. First-run wizard initializes a blank brain, adopts an existing Zhinao directory read-only, or fills in only missing skeleton files; existing files are never touched.

A graph of your memory store for DSH: one node per real memory, and every edge must state why the two are connected — a quoted keyword, a shared term, a project, or temporal adjacency. Pure filesystem reads with no model in the loop; unreadable sources are reported, never replaced with fake nodes.

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.