Plugins

Right-sidebar Git review panel for DSH: staged and unstaged change tree, inline and side-by-side diffs, stage/unstage/discard, commit and push, AI-generated commit messages, and line blame. A fork of sadgsk/dsh-review-panel 0.3.1; install either this or the upstream panel, not both.

Project control plane with durable tickets, replaceable DSH sessions, a project matrix, and bidirectional UI navigation.

File-state cache skill for coding agents: one explore call replaces ls+grep+read, reads remember they already happened, and edits return a diff plus the exact changed line range instead of a full re-read. State is a JSON cache on disk, so it survives across tool calls and restarts. Requires Python 3.8+ (standard library only).

Adds a Vivado session preset to dsh with an FPGA engineering-discipline persona (global serialization, pure-ASCII paths, evidence-first conclusions, detached long builds) and mounts eight bundled AMD/FPGA skills from the package itself; installing the preset needs no Vivado or vivado-mcp installation.

Save conversations, manage notes with images, export files, and sync across devices through your own private GitHub repository.

Makes identifiers inside inline code in chat clickable; resolves a definition, then a wrapper, then the next occurrence, and opens the file at that line in the sidebar preview.

Connects DeepSeek Harness to AIyting's image generation MCP endpoint and registers four tools: aiyting_image_catalog (models, routes and specs), aiyting_image_settings (read, quote and save parameters), aiyting_image_generate (return a quote first, and submit only with an explicit credit ceiling) and aiyting_image_task (task lookup, waiting, and a local per-account ledger for unfinished jobs). A sidebar page signs in with an AIyting access key, shows points, today's usage and daily quota, logs out, and keeps per-conversation defaults for model, route, aspect ratio, resolution and count.

Connects DeepSeek Harness to Postel over MCP: search a library of X posts that went viral by topic, write posts and X threads in the user's saved voice, and save, schedule or publish them to X, LinkedIn, Bluesky and Mastodon; adds a postel-writing skill. Research works without an API key.

Manage Zuad digital signage programs, media, playback schedules, and devices through DeepSeek Harness. Requires an existing Zuad signage backend and an account on it; you sign in from the plugin settings and the password stays local.

A Windows-only DSH plugin that cleans up the taskbar in one click and closes windows the graceful way, sending WM_CLOSE (exactly what Alt+F4 sends) so applications can save and exit. Cleanup is preview-first, listing every window that would be closed before anything happens, and the execute action stays disabled until you have previewed. Windows are shown two ways, a compact icon grid where one click closes that single window and a per-app detail view with full titles plus a close this whole app action and a per-window close button, so you can close one window, every window of one application, or everything at once. Elevated administrator windows are supported too, through a single UAC prompt that sends the same graceful close and reports the real result instead of pretending success. Leftover empty console shells, meaning consoles whose interpreter has no business child process left besides conhost, can be hidden losslessly or genuinely closed, and that action is restricted to bare cmd, powershell, pwsh and python prompts. Hard guards keep the DSH host and its whole process tree, Fluent, MPI, ANSYS and solver processes, the foreground window and the plugin itself out of reach, and a persistent exemption whitelist of process names and title keywords is stored in ~/.dsh/console-sentinel/whitelist.json and editable from the Console Sentinel page under Settings, which also shows live window status.

Connects the CallAI SEO MCP server: 10 SEO data tools plus a generic DataForSEO request tool for Google/Bing SERP (with AI Overview sources), keyword volume and difficulty, long-tail ideas, competitor keyword gaps, backlinks and page audits. Includes a callai-seo skill. Requires a CallAI API key; pay as you go.

Keep conclusions alive across context compaction: the model writes a task checkpoint and the plugin re-injects it into the system prompt's first node — the span compaction never touches, so it survives any number of compactions. Four-tier injection (0/95/175/≤12000 chars) scales with session relatedness; checkpoints live in the plugin's own folder, never in your workspace.

Four-layer memory for DeepSeek Harness, ported from the memory design of NoMindSama/qq-dsh-bridge (MIT) with the QQ channel removed: an append-only dialogue log, a weighted long-term fact store with decay and one-way archiving, self-notes the agent writes about itself, Chinese bigram recall over the raw log, and incremental AES-256-GCM sync to a private git repo where only ciphertext is stored. Archived sessions drop out of recall without losing their history.

Cross-session long-term memory backed by Supermemory: pre-step semantic and chunk recall with per-session deduplication, debounced transcript upload, background LLM fact extraction (add/update/delete) with bigram and semantic deduplication, memory_search / memory_save / memory_forget tools, global or per-workspace container scoping, and a Plugins page UI for API key storage, memory CRUD, recall preview and activity log. Requires a Supermemory API key (a free monthly quota is available), and conversation excerpts are uploaded to Supermemory's cloud.

Adds custom task groups and an activity bell to the sidebar: drag sessions into or out of a group, reorder them by hand, collapse groups, and see running, waiting and unread sessions in one place.

A self-hosted digital-life companion for DSH. Three slow-moving hormones (dopamine, cortisol, serotonin) set its mood and tone, a memory layer turns chats into events and facts with version chains and a forgetting curve, and it writes, hot-loads and unloads its own organs (tools) when a capability is missing. It handles text, images, stickers, voice notes with text to speech and speech recognition, and file uploads; the web space holds diary posts and guestbook comments, and it starts conversations on its own schedule. The built-in web server listens on 0.0.0.0:2332 by default, so create the owner account before exposing the port.

Persona, mood, long-term memory and per-person ledgers for a DSH agent, with a portable soul pack for moving between machines.

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swaps, misreported usage, truncated context and injected prompts; keys are read from environment variables.

Switch OpenAI models between Codex-style Responses WebSocket transport and SSE from the composer, inheriting DSH provider settings with an optional priority-tier toggle.

Google Antigravity model provider based on LiZhenNet/dsh-antigravity, with a multi-account pool added. Do not install it in the same profile as LiZhenNet/dsh-antigravity: both register the same bundle id (dsh-antigravity) and the same npm package name.

Registers two LLM account pools as model providers: TeleAgent (China Telecom TeleAI; paste a token once) with a daily 09:00 UTC+8 full-pool check-in — currently check-in, balances and model listing only, since its chat is blocked by the client signing key — and AutoClaw (Zhipu desktop, Windows), whose tokens are decrypted from the local DPAPI-protected credential store and whose chat streams through the desktop bridge. Both pools report credit balances and model catalogs; quota-triggered failover across local desktop instances is automatic, while switching the AutoClaw account is an opt-in setting (off by default). Panels ship in settings and the left sidebar.

Cost display for AiSpot (sapi) relays: crawls the provider's group list from its public pricing endpoints instead of hardcoding it, lets you pick the active group from a dropdown in the conversation header, and shows a per-turn cost at the end of each turn plus a session total that recurses through every subagent subtree. Switching groups re-prices all history instantly, because the host publishes token buckets only and the browser applies the live rates.

All-session token usage dashboard in the sidebar: total and peak tokens, usage streaks, a 53-week activity heatmap, 7/30-day trend, per-model usage and a session ranking. Folded locally from the profile session projection cache, so sessions written by older session formats are counted too; no network access, and the read-only summary route refuses non-loopback peers.

Composer token pill for the current session: total tokens plus uncached input, cache read, cache write and output, with the cache-hit share. A pure client consumer of the session tokenUsage projection — no host service, no file access, no network requests.