Plugins

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Windows minimal agent preset for DeepSeek Harness: fixed one-line persona, three tools, no runtime context.

Sky: Children of the Light skin for the dsh web UI - light children on a glowing star map, candlelight gold and starry night.

QA orchestrator plugin for DeepSeek Harness: an agent explores your app and leaves evidence, then the explored path replays deterministically. Drives the browser, macOS desktop, iOS and Android drivers.

English edition of Weiwen's Law (KISS's Law): the first and only domain-agnostic white-box causal adjudication middleware for AI agents. Unlike domain-specific causal-inference tooling (statistics/economics/ML) or evidence-gated agent firewalls, it adjudicates *every* tool call along a deterministic structural causal chain (R->S->D->H->M) before execution - across any domain, with no training or per-domain tuning. It blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost.

Git worktrees for DeepSeek Harness: five agent tools, a New Session picker that starts a session inside one, a sidebar tab for the uncommitted diff, a panel that unarchives or deletes archived sessions, and double-click rename. Removal refuses uncommitted or untracked changes and never removes the main worktree.

Adds file-backed Chinese web-fiction planning, chapter writing, consistency review, rollback, and style-profile skills.

Runs DSH's stock bash tool on Git Bash for Windows, so commands go straight to bash -c instead of being re-parsed by the pwsh tool.

Per-message delete for DSH: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.

Kami-inspired editorial skin for the DeepSeek Harness web UI, with a warm parchment canvas, ink-blue accent, serif typography and hairline borders in light and dark palettes.

Aqua glassmorphism theme for the DeepSeek Harness web UI, forked from upstream and repaired to load on DSH 0.1.2-rc.1: mica and compatibility modes with adjustable blur and frost, fluid or wallpaper backdrop, background brightness, and a master switch that restores the stock UI.

Writes the harness agent live state (thinking, working, waiting, done, error) to a state file that a bundled Electron Live2D desktop pet polls, so the pet bubble and face follow what the agent is doing.

TraceScope DeepSeek Harness plugin 鈥?embedded React Slot UI + same-origin APIs

A faster, more efficient, and more accurate coding Agent preset. On 100 hard SWE-bench Pro tasks selected using multidimensional difficulty criteria, average elapsed time decreased by 36%, average input tokens per task decreased by 17%, and accuracy increased by 5 percentage points.

Scopes system-prompt personas by workspace path or session id (exact, prefix, contains, regex), with an optional default persona for sessions nothing claimed, a 人设 tab on the conversation showing the prompt actually sent, import and export of the list, and a switch that refuses tool writes to the persona store.

Command Code plan quota in the DSH sidebar above Settings: 5-hour, weekly and monthly windows as used percentages with reset countdowns, a /quota command, and a zero-dependency CLI. It reads the key from your own provider route, so it needs no configuration and no other plugin.

A native reasoning-effort control for the composer: a blue-to-violet tier bar with a starfield and a sheen sweep. It owns the model seat and drives the official model-directories service, so the ladder comes from each model's own reasoning declaration and no other plugin is required.

Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.

Manage DSH skills and commands from Settings: list, enable/disable, edit, delete and add skills across global and project scopes, and save reusable prompts as slash commands.

A local-first personal state record and decision engine for dsh: keeps every input byte-for-byte with line-level provenance, argues against its own conclusions by generating defeaters first, ages each stored fact with its own TTL, and reports where a decision rests on nothing at all.

Merges other sessions' context into the current turn: evidence-weighted conflict resolution, retraction of claims whose premises were retracted, trust labelling that resists cross-session prompt injection, and budget-bounded packing. Ships a benchmark.

One plugin for DeepSeek Harness with durable autonomous loops, sidebar GitHub discovery, AI-assisted installation, and workspace shortcuts.

Turns the MacBook keyboard Caps Lock light into an agent status light: on while the agent works, flashing when it waits for your approval or answer, off when idle.