Plugins

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Component checklist for the shared Semi Design package used by tnnevol DSH plugins, opened from a `Semi UI` button in a conversation header: 35 components plus a multi-account case page, organised into seven sidebar groups from inputs, forms, selectors and trees to tables, cards, overlays and feedback, each rendered live with a one-line description and a page outline, with light, dark and follow-system preview. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-semi-ui-showcase`.

Remote control for dsh web from a phone browser: the plugin adds an in-harness Settings panel (cloud/self-hosted mode tabs, account login, bridge start/stop, feedback) with same-origin /dsh-remote relay routes; the desktop bridge and self-hosted relay-router in this repo tunnel the local dsh web to a phone PWA with access-key auth, a live device list and optional traffic quotas.

Remote control for dsh web from a phone browser, from anywhere (no public IP needed): hosted cloud relay works over 4G, or self-host the router; one command installs the desktop bridge and this in-harness Settings panel (cloud / self-hosted / WeChat-bot tabs, account login, bridge start/stop, feedback); the tunnel data plane is end-to-end encrypted (E2EE phone↔desktop, with a QR / one-time-link desktop grant so you never re-type the password), with HTTP/WebSocket pass-through, access-key auth, a live device list and optional traffic quotas; the WeChat bot channel is bound by QR scan and pushes task-finished / error / stopped events to WeChat, where one number in reply approves or denies a pending decision and continues the current task — WeChat messages travel only between Tencent ilink and the local bridge, never through the relay.

Component checklist for the shared Semi Design package used by tnnevol DSH plugins, opened from a `Semi UI` button in a conversation header: 35 components plus a multi-account case page, organised into seven sidebar groups from inputs, forms, selectors and trees to tables, cards, overlays and feedback, each rendered live with a one-line description and a page outline, with light, dark and follow-system preview. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-semi-ui-showcase`.

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.

Mobile-first Web UI quality-of-life pack for the DeepSeek Harness: a Chrome-style active-session tab bar, full-screen sidebar swipe open/close, overlay sidebar, collapsed-sidebar recents, keyboard-suppressing session switching, viewport/IME keyboard adaptation, touch feedback, code/table inner scrolling, hidden permission dropdown, a full-screen settings rewrite with tab memory, and a compositor-driven status pulse, no-touch-drag long-press protection — 14 features, each independently toggleable from the Settings QoL section with instant effect, persisted per browser in localStorage; pure client-side CSS/JS, mobile rules locked to viewports of 768px and below so desktop stays untouched.

Select browser elements directly during Vibe Coding and send structured visual feedback to the DeepSeek Harness Agent.

Plan review with anchored annotations and structured feedback back to the agent.

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Karpathy LLM Wiki pattern knowledge base for DSH: wiki-write/wiki-search skills, zero-dependency pipeline (lint/index/mnemon memory sync/quality feedback), minimal lifecycle plugin injecting schema + knowledge preview, SiliconFlow semantic recall via an Ollama-compatible proxy.

Reproducible science workbench: agent-driven cells, inline figures with feedback/rerun, manifest provenance, environment snapshots, and publication-grade figure skills (9 bio_* tools + workbench UI).

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.

Adds a take screenshot tool plus two optional automatic capture points, putting the screen into the conversation as an image block; requires an image-capable model.

Four GitHub workflow skills for PR triage, review feedback, GitHub Actions diagnosis, and safe draft-PR publishing, reusing existing DSH capabilities with gh/git fallbacks.

Maps locally analyzed system audio to music-reactive conversation effects, rhythm-game judgements, score and combo feedback, and optional RGB spectrum bars in DSH Web.

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.

Audible feedback for the DSH web interface: button presses are classified by semantics (normal, primary, toggle, send, close, danger, link) and the current session's task transitions (started, finished, failed) plus any pending interaction play a cue, each scenario with its own cue picker and switch on a settings page. All 78 cues and 12 sound packs are synthesised in the browser with the Web Audio API, so the package ships no audio files and makes no network request. A community port of dsh-plugin-uisfx to DSH 0.2.0, with the ported changes recorded in PROVENANCE.md.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

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.

Model-linked characters and a shared world for DSH, with separate editable personas and memories, optional AI diaries and sleep consolidation, Chinese/English controls, task-aware desktop pets, themes and usage statistics; updates preserve user customizations. Supports Windows, Linux and macOS; see the guide for each system's installation requirements. Diaries and consolidation consume tokens. Before installing or updating, we recommend closing visible desktop pets and bubbles; open files may cause installation to fail. Codex and OpenAI API account queries have been user-validated; other sources await user validation and feedback.

In-conversation source deck for DSH Desktop: the current chat model runs LLM search rounds, candidates render as GitHub-aware cards, and keep/exclude feedback, favorites, and the selected sources stay in the same conversation.

Memory-assembly team for DeepSeek Harness: every message triggers a five-step cognition loop (judge, retrieve, assemble, feedback, calibrate) carried by role-playing subagents (judge, retriever, archivist, advocate, editor, scribe), using BM25 retrieval, time-ordered material, and LLM assembly to build useful material packs injected into linghun. Works with dsh-linghun.

Native DeepSeek Harness plugin: feeds every prompt into the local agent-feedback-loop capture pipeline and injects compiled recurrence rules back as context.