Plugins

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Pre-execution guard that blocks destructive Git and filesystem commands and access to secrets such as SSH keys and .env files before a tool call runs.

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

WYSIWYG Markdown editor in the DSH right sidebar, built on MarkText's muya engine: open a .md file, edit it as a rendered document, and save back through ctx.fs with a version guard.

DeepSeek Harness 插件：本机 Stable Diffusion 生图九件套（文生图/图生图/蒙版重绘/只生成脚本/双版本对齐脚本/C 档本地注入命令/模型清单/服务管理/完整性检测）+ 违规分流协议 + C 档选项表（A 档出图后罗列模型/LoRA/比例等，一句话即可重出图）；C 档蒙版支持鼠标手绘。跨机器零适配——SD 目录自动探测，找不到可一键自举安装，产物目录自动落在会话工作区。

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file. Every step the `MEMORY.md` index (the project store if there is one, plus a global store under `$DSH_HOME`) goes into the runtime context, so recall does not wait for a file read. The index has a hard cap, 200 lines / 25 KB by default, enforced by `ctx.tools.guard()`: a write that grows an over-cap index is denied, a rewrite that shrinks it passes. A read-only sidebar Memory page lists the notes by type. The plugin never writes memories on its own. An experimental companion mode adds note types for a persona's own life. The same store also works with Claude Code, Codex, Kiro and OpenClaw.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

Pre-submit pull-request hygiene checks inside DeepSeek Harness: scans the current diff for TODO leftovers, hardcoded secrets, and non-conventional commit subjects.

Counts persistent operations within a turn and escalates on the total: a reminder first, then an explicit stop instruction, then an approval prompt. Reads the session sandbox mode on every call, and stays silent under read-only and workspace-write.

All-in-one companion for the DSH web GUI: a balance whale widget with today's usage, per-turn cost and peak/off-peak pricing, an editable bubble queue and sound effects; a 106-clip transparent desktop pet with spring drag, throw, screen roaming and clones; a QQ message card bridged through SnowLuma for reading history and replying; Bilibili dynamics and comment interaction with a fish guard and a day/night schedule; and local, redacted two-way memory. One plugin; data stays on the machine. Runs on Windows 10/11 only.

Visualize the DSH process network path on Windows or WSL with layered DNS/TCP/TLS/HTTP probes, detect stale proxy configuration, and apply snapshot-guarded repairs.

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

Bioinformatics agent preset with 17 BioDSH analysis skills (single-cell, bulk RNA-seq, survival, regression, ANOVA), a 2000+ skill library searched by a skill_library tool, per-message skill selection and a time/step convergence guard.

BioDSH for DeepSeek Harness: a bioinformatics agent preset with BioDSH skills, a 2000+ skill library, automatic skill selection and a convergence guard

Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.

Daily game automation on Windows for Genshin Impact, Honkai Impact 3, Honkai: Star Rail and Zenless Zone Zero: a scheduled task per game drives BetterGI, the game-daily skill family, March7thAssistant or ZenlessZoneZero-OneDragon, with per-game switches, a foreground guard, in-run supervision that only steps in on trouble, and one report session per game that later results are appended to. Requires the DSH desktop app and the matching external engine installed.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Novel-writing guardrails: 24 novel_* tools enforce fact-ledger consistency, outline and chapter gates, a deterministic machine audit with a zero-token AI-flavor scan, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, whole-book checks and batch drafting with checkpoint resume.

Raises the local Host's HTTP header budget to 64 KiB and retires stale dsh-auth-* launch cookies on each response, so a fixed profile cannot lock itself out of the desktop welcome handshake after roughly 72 restarts.

Feishu/Lark bridge for DeepSeek Harness: scan-to-connect PersonalAgent binding, streaming cards, git-worktree project workspaces, parallel per-scope tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian that still answers in Feishu after dsh crashes.

Research-only trading workbench bundle: typed market-data provider seam with a CSV reference provider, multi-timeframe indicator regime snapshot and OHLCV tools, interactive chart cards in dsh web with provenance-gated model annotations, and a risk-guard denying execution-shaped tool calls at tools/pre-execute.

Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory. v0.11 added a bilingual settings panel whose copy and sidebar label follow DSH language setting (中文「记忆」/ English "Memory"); v0.12 added the shared cross-plugin speech floor, a context-sensitive tone section and a weekly growth recap; v0.13 declares its DSH compatibility via engines.dsh (official 0.2.1-rc.5 series; older hosts are refused by the gate), adds a "Review now" button (POST /api/memory/control, action growth-now) that sends one growth recap immediately while still respecting the speech floor, panel accessibility (aria labels, status and alert roles, focus-visible rings), and the public PROACTIVE-PROTOCOL.md. v0.14 adds per-session memory: a composer chip with a dropdown (this session / workspace default), the /memory on|off|status command, and a settings-panel switch all flip the same gate — off means no boot injection, no digest/recall nudges and no last_access stamping for that session (nothing is deleted); disabledWorkspaces lets whole projects default to off, and session choices persist for 7 days. v0.15 adds a Basic soul (quick forging) card: my name / what I call you / baseline persona, saved into a managed block inside SOUL.md (the rest of the file is left untouched) and marks BOOTSTRAP complete; existing chat-forged souls are echoed from the SOUL text, and the boot block now asks the agent to remind the user to forge first when no soul exists yet. v0.16 turns the memory graph into an interactive 3D sphere (Canvas, zero dependency): drag to rotate, wheel to zoom, drag nodes to arrange them in 3D, double-click empty space to reset, auto-spin (reduced-motion aware); hover or click a node to instantly light up its neighbours (displacement+duration click threshold), and colours adapt to light/dark panel themes. v0.17 adds graph search (ranked matches, the camera flies to the hit and lights up its neighbours), Reveal in Finder / Copy path for any node (the host command is awaited, and the absolute path is copied automatically when reveal fails), Windows support (path-variable expansion, CRLF parsing with style-preserving writes, explorer /select, argv and exit-code handling, case-insensitive workspace matching), plus a much shorter README with real screenshots. v0.18 (issue #8) adds a boot snapshot mode: session freezes the boot block for the session so mid-session memory writes no longer invalidate the prompt-prefix cache (the volatile recent-log tail now rides in its own late context segment), with live kept as the default; double-clicking a memory node now opens the note in the DSH right sidebar (falling back to Finder/Explorer). v0.19 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.19.2 or newer (0.19.5 is latest). Settings, dashboard and composer chip keep working on both the legacy and the rc.2 host APIs.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.