Plugins

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Local literature knowledge-base RAG: 10 tools (kb_ingest, kb_search, kb_rag, kb_zotero, kb_dedup, kb_clear, kb_fetch, kb_scope, kb_stats, kb_status), hybrid BM25+vector+reranker search, cited QA with clickable DOI links, all-local bge embeddings over a single-file SQLite index. Needs Python 3.9+ with pymupdf, faiss-cpu and sentence-transformers; the `npx dsh-kb-rag-install` installer sets those up and pre-downloads the model.

eDEX-UI-style shell over the DSH web GUI: system-telemetry left bar with per-core CPU sparklines, encom-globe world-map right bar with up/down traffic chart, filesystem browser with file preview, and a terminal-styled composer that follows the active workspace.

Server card dashboard for DSH: per-host status, CPU, memory, disk and latency, with one-click xterm.js SSH terminals; imports ~/.ssh/config and mounts as a better-sidebar tab or a standalone right drawer.

Cross-session memory plugin for DSH (v0.6.1, npm @asherliner/dsh-memory-connect): auto-extraction, SQLite FTS5 indexing, RRF semantic recall injected into the system prompt every turn, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. v0.5.0 added temporal context graph (valid_from/valid_until/supersedes, append-only corrections via reviseMemory), trust model (recalled history injected as untrusted reference, current instruction always wins), turn-end summarization. v0.6.0 added local semantic embeddings (BAAI/bge-small-zh-v1.5 via embed_server.py, cosine + RRF fusion with FTS5, no cloud calls, ~232 msgs/sec on CPU). v0.6.1 fixed ~ expansion in path config. Zero-config install.

Local OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.

Renders Wallpaper Engine scene wallpapers in real time in the browser (three.js player plus a Rust/WASM CPU particle simulation) and plays video and web wallpapers, falling back to the preview image, with no Wallpaper Engine runtime required. Scans the local Steam workshop library (431960) by auto-detection or a manual path, and offers a settings panel for wallpaper selection, library and engine directories, glow, pause and quality.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

DSH tools for reproducing and validating the ml-quant-trading protocol v1 CPU benchmark, then drafting an issue-ready report. Requires a local clone of initial-d/ml-quant-trading (set as the workspace or repoPath) plus Python and PyTorch; this plugin does not fetch the repository or install its dependencies.

Convert Office documents and PDFs (including scanned ones) to structurally formatted Markdown via a CPU-first routing OCR pipeline (RapidOCR/SLANet/FormulaNet).

DeepSeek Harness plugin for SCNet HPC: SSH setup, CPU/DCU Slurm jobs, cluster probing, compute-node diagnostics, and Hygon DCU/DTK guidance.

Purple-white desktop pet that docks to the screen edge and shows real-time CPU, RAM, GPU and NVMe temperatures with hardware info.

Displays real-time CPU and memory usage for the machine running the DSH Web server.

System status floating widget: live CPU/memory/disk usage in the bottom-right corner of the DSH Web UI with threshold colour warnings.

DSH 插件：用于局域网内设备监控，在右侧边栏（结合 dsh-better-sidebar）登记最多 10 台设备， 通过 SSH 定时采集运行指标、画波形图，并对 CPU / 内存 / 磁盘 / 温度做阈值告警。

DSH 侧栏实时硬件监控：CPU / GPU / 内存 / 磁盘一页看完，每秒刷新，每个读数都能下钻到是哪个应用。支持容量与内存耗尽预测、阈值告警与 NDJSON 导出。纯 Node，零运行时依赖，完整功能仅 Windows。

Windows host performance from WSL: CPU, memory, disk and top processes.

Service control panel in DSH Web settings: live host info (PID, versions, uptime, memory/CPU trends, active sessions), npm update banner, and a confirm-guarded graceful stop that warns when tasks are running and can wait for them to finish.

Sidebar system monitor for the DSH Web UI: live host overview (CPU/memory/network/disk), process list, and Docker container status, all read-only.

Read-only Windows device information tools: one agent tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers) via WMI/CIM and Node os collectors.

蛋白质结构预测与设计插件：序列设计（ProteinMPNN/SolubleMPNN/LigandMPNN）、结构预测（ESMFold）、复合物界面筛选、序列理化打分与多样性聚类——零手动自举（本地 CPU/GPU 自适应），供 dsh-bio-genie 消费 | Protein structure prediction & design toolkit for dsh (sequence design, folding, interface screening)

Real-time host performance monitor for the DeepSeek Harness right Sidebar: CPU / memory / swap gauges, a GPU clock and VRAM line, CPU / GPU / motherboard / drive temperatures, a sortable process table, and a keep-awake toggle for remote sessions — on Linu

Live btop-style CPU/memory/temperature/GPU monitor tab for the DeepSeek Harness web GUI.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.