Plugins

Input prediction for the DSH composer: your next prompt suggested as ghost text after each turn, accepted with Tab. (autocomplete / input prediction / prompt suggestion)

Unofficial provider that connects Tencent CodeBuddy open platform models to DeepSeek Harness, with automatic model discovery and a settings page for the API key.

Desktop half of the dsh browser extension: mounts a token-authenticated WebSocket bridge on the dsh webserver and exposes the browser_* tools that let the model read the tab you are on as text and act on it, with image recognition off until the user enables it.

Windows Computer Use for DeepSeek Harness with screenshots, UI Automation, 18 desktop tools, per-Agent activation, human-input handoff, approval prompts and prebuilt native workers.

Talk about everything in one chat (the main chat): each message is routed automatically to the topic it belongs to, each topic runs in its own background session with its own context, and existing DSH chat history is organized into topics.

Hierarchical Claude Code-style memory: user + project scopes (project memories committed to git for the team), MEMORY.md index auto-injected at session start, context-window guards, pure files.

Lifecycle notification layer for AI coding agents — DeepSeek Harness 0.2 plugin: OS notification, in-page toast, and optional sound when a turn, background job, review, or failure needs you.

Use your logged-in web AI (DeepSeek, GLM, Kimi, Qwen, Doubao...) as model providers in DeepSeek Harness. Web models emit tool calls, DSH runs them under its native permission system, and results return to the same web session. No API keys.

DSH adapter bridging DeepSeek web chat and DeepSeek Harness with automatic DSM-tag harvesting, memory injection and write-back, full-answer saving on the web, a DSH sidebar for browsing and manual injection, named-entry retrieval, general/non-general classification, and transactional memory compression; works with the separately loaded Chrome/Edge extension in extension/ and the local @zoria-lind/dsh-ecolink-service, which the adapter can start automatically.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.

Manage VPS servers over SSH key login: 22 zero-token /vps- commands (status queries, recipe installs with a plan and /vps-yes confirmation, reboot that waits for the machine to come back), an in-conversation terminal (xterm.js over ssh -tt) for interactive programs, 5 agent tools with risk-tiered confirmation, file backup with automatic restore and a firewall/SSH safety net, 29 built-in recipes, and a settings page for adding machines.

Automatic cross-session memory for DeepSeek Harness, backed by a local EverOS service.

Phone and remote access to the DSH Web UI: scan a LAN QR code, or reach your PC from anywhere through a self-hosted relay server you run yourself instead of a cloudflared tunnel. Per-device credentials that pair, list, and revoke individually, and several PCs sharing one relay with automatic failover.

Local model plugin for DeepSeek Harness: manage GGUF models in settings, auto-launch llama.cpp on first message, and auto-unload after 5 minutes of idle time to free VRAM.

Cristiano Ronaldo desktop pet for DeepSeek Harness: a chibi Portugal number 7 mascot in a bottom-right overlay whose animation follows the agent state — dribbling while tools run, thinking during a turn, waiting at approvals, diving on errors — and jumping in a SIU celebration with a host-process sound when a turn completes; it can be dragged, looks at the cursor on hover, dives on a triple click, and a settings panel manages several pets and imports custom spritesheets. It also runs as a borderless, always-on-top native Windows window that keeps living after the browser is closed: hovering shows the current workspace and conversation title, double-clicking opens the Harness page in Edge, and dragging, mouse-wheel resizing and a right-click menu work there too, sharing position, size and behaviour with the web panel. Pet sheets may use any cell resolution and scale preserving aspect ratio (atlas.scaling: smooth | pixelated). v2.2 adds a video route — feed it a clip (green screen or ordinary footage) and its real motion becomes the pet animations, via automatic backdrop sampling, chroma keying with spill suppression, motion-based segment splitting and union-bbox alignment; already-extracted PNG frames work too, with no video decoder installed, and the clip audio can be cut into per-action sounds. Pets can also be published to the community gallery under the DPSL-1.0 sharing declaration, and installed from it in one click. v2.3 adapts it to DSH 0.2 desktop clients — the celebration sound now falls back to spawning PowerShell when the host no longer provides the shell service — and makes a single click play a short, configurable taunt animation (`interactions.clickAnim`).

Modular execution discipline and autonomous steward for DSH: evidence-first routing across 44 canonical skills, durable state planning, verification gates, fail-streak recovery, and interactive web dashboard.

COM-driven real Microsoft Office automation for DeepSeek Harness: drives a running Excel/Word instance through OfficeMCP — VBA macros, pivot tables, live formula recalculation, and deep document layout; plus an accounting suite (double-entry journal posting with debit/credit balance check, and SUMIF general ledger).

Redirects DSH downloads, artifacts, caches and temp files to user-specified drives (auto-picks the largest non-C drive), injects a path-discipline prompt into every session, and ships a disk_guard tool for status and cleanup — keeps the C: drive from filling up.

About section for the DeepSeek Harness settings: version info, npm latest/next update check with one-click install and auto-restart, and GitHub release history.

Recall, edit-and-resend and regenerate, plus in-conversation versioning: a timeline of every rewind, artifact rollback (git-first, snapshot fallback), a fork map of explored paths, session lineage, and a real-time watchdog that snapshots the log at the first sign of concurrent writes. Edits auto-stop the running agent (official cancel/whenIdle) so rewinds never corrupt the durable log or break /compact.

Message-level full-text search across DSH sessions via an FTS5 trigram index (user / assistant / steering / tool with per-kind filters), deduplicated results across fork/continued sessions, read-only context preview with auto-scroll to the focused message, one-click jump to the real session, and incremental/full index rebuild with health check; zh/en i18n follows the Host locale service.

Peak-hour auto session gate: weekend mode + global peak auto-pause + session-level freeze/resume + backend auto-retry, auto-resume on off-peak.