Plugins

WispOps (dsh-wisp-ops): multi-host server operations plugin for DeepSeek Harness — fleet inspection, disk & recent-file analysis with omics cleanup advice, security triage, scheduled per-server reports, human-approved sudo

Run Python on the local NVIDIA CUDA GPU from DeepSeek Harness: device status, foreground and detached jobs, durable logs, and a measured peak-VRAM figure per run.

A transparent, draggable performance HUD for the DeepSeek Harness Web UI: CPU, GPU and memory usage in three compact rows that float directly over the interface without any card background, snapping to the nearest window corner so resizing or maximising keeps them in place; CPU package temperature comes from an optional elevated helper (LibreHardwareMonitor + PawnIO) and the plugin itself stays at a fraction of a percent of CPU. Windows only.

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.

Shows a Spark Scope card at the bottom of the dsh sidebar: model server decode and prefill rates with sparklines, running and queued requests, KV cache, TTFT and TPOT p95, and GPU temperature, power, load and memory for each DGX Spark node. Read-only; needs a running Spark Scope server. Works in dsh web and the desktop app.

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)

Host performance monitor in the right Sidebar: CPU, memory and swap gauges, a GPU clock and VRAM bar, CPU / GPU / motherboard / drive temperatures, and a process table sortable by CPU, memory or name.

Multi-instance ComfyUI orchestration: probes every configured ComfyUI endpoint for its GPU, free VRAM and queue depth, then dispatches a generation job to the idlest eligible instance. Ships three tools (comfyui_farm_status, comfyui_farm_pick, comfyui_farm_run). An instance is eligible only if it is reachable, has at least the requested free VRAM, and its queue is no deeper than the configured ceiling; eligible instances are ranked by free VRAM minus queue depth times a weight, so an idle shallow queue wins over a busy large one. Zero runtime dependencies. Optional retry on probe failure, because a single timeout across an SSH tunnel is not proof that an instance is down.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

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.

Adds /dev/dxg and /proc read-write grants to the DSH Landlock sandbox on WSL2, so CUDA is available inside a confined agent bash session.

A switchable WebGPU black-hole theme for the DeepSeek Harness Web UI that retains the built-in Dark palette and animates only the new-session background.

Keeps a local model's context at a size the GPU handles well: measures prefill speed on every request and, before each step, warns or compacts early on a hard token ceiling, an observed time-to-first-token budget, or a predicted cold-prefill budget; /context-budget shows the numbers and the cost of compacting now.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

DSH plugin (dsh-desktop-launcher) that launches the dsh-desktop Windows Electron shell from the conversation: double-click to run the DSH web in a standalone window, region screenshot with GPU-accelerated selection that auto-pastes into the chat (works with vision bridges), system tray, session manager, auto environment setup, configurable port, single-instance lock.