Plugins

Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-whisper transcribes the audio track, so the agent reads real pixels frame by frame instead of trusting a text summary. Fully local, nothing uploaded; reports honestly when the audio has no speech. Windows only; needs Python 3.10+ and ffmpeg installed, and the first video_eyes_setup run downloads about 700 MB (faster-whisper and its model).

Deliverables registry for DeepSeek Harness: agents register the final artifacts of a task (reports, pages, documents, sheets, images, datasets) into one settings section and manager page that store paths only, never copies, and remove recoverably; a standalone CLI (add, list, stats, check, remove, restore) reads and audits the same registry outside the app.

Requires JDK 11+, the DM JDBC driver and SSH access to the target instance. Inspect Dameng database instances, assess security and recovery conditions, and generate filterable reports with shared evidence.

Requires Claude Code installed and signed in on this machine. Delegates coding tasks to the local Claude Code agent through the Claude Agent SDK, reports which files changed, supports one-command revert, and adds a Claude Mode toggle to the composer.

Turns a Minecraft Java save into a Blender cover or animation: scans the .mca region files for flat open ground, exports the terrain to OBJ, and drives Blender headless with MCprep materials, the BPS character rig and three-point lighting. After each render it reviews the frame with OpenCV for facing, ground contact, exposure, lighting and composition, then re-renders with adjusted parameters when a check fails. Requires Blender 4.2 LTS or newer and Python 3.10+ with opencv-python and numpy; the first run assembles the Minecraft assets with the bundled setup command.

Windows-only game crash diagnosis from Event Log, WER reports and crash dumps, with a diagnose_game_crash tool and an optional background notifier.

Reads the installed plugins, MCP servers and skills, groups them by capability, and reports which preset each belongs in; can register one preset per category on request.

Read, edit, export and verify Excel VBA projects through a real Excel COM instance: modules, UserForm code, procedure lists and .frm/.frx exports. Windows only, with desktop Excel installed, Python 3.10+ with pywin32, and AccessVBOM=1.

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

Adds a permanent Delete session action to the sidebar session menu, behind a confirmation dialog that reports the log size, running turns, subagents, background jobs and reminders bound to the session; the id is then released from the live, archive and workspace registries, so the row stays gone on refresh instead of folding back in.

Goal Map shows a read-only goal-to-plan progress route, session mindmap and step list using reported plan progress, without starting tasks or model calls. Beta.2 supports DSH Web 0.2.0-rc.2 or 0.2.1-rc.2, with Node.js >=24.

Adds an Insight tab next to the conversation and trajectory tabs in DSH: calls a model to interpret tool calls turn by turn, and supports a custom prompt.

Per-channel credit balances for the Our Free Model gateway in the DSH sidebar: one always-on card covering the channels the gateway supports (unconfigured channels stay hidden), collapsed to the channel the current conversation uses, expanded to one row per channel with a bar and remaining amount, with per-channel visibility toggles on the plugin detail page.

Slims oversized MCP tool JSON Schemas per agent without changing dispatch, and reports token usage, cache hits and context composition on a settings page.

Imports SillyTavern AI presets as switchable, editable prompt layers: preserves the raw JSON, edits prompt order and sampler parameters, previews the injected System Prompt, exports back to SillyTavern-compatible JSON, and archives or permanently deletes presets with confirmation. Applies temperature and maximum output tokens to Harness requests; other sampler fields are preserved and exported but not applied.

Link local project directories from a project context menu, with scoped search, source reading and explicit per-session snapshot synchronization. Supports DSH 0.2.1-alpha.4 and 0.2.1-rc.2 only.

Responsive card grid for the DeepSeek Harness composer model picker, grouped by provider. Host-only: injects a stylesheet through webserver/index-inject without rebuilding the client bundle, and supports both the stock picker and the dsh-peakrate menu.

Global back/forward navigation for the DeepSeek Harness Web UI: remembers every session and whole-page panel you visit, shows a configurable 1-7 entry history strip you can click, and supports browser-style shortcuts plus mouse side buttons.

Opens .blend files in the right-Sidebar document preview: Blender headless exports a cached GLB with scene statistics, rendered by a dependency-free WebGL viewport. Requires Blender 3.6+ on PATH (or set blenderPath).

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

Exports the plugin profile together with selected $DSH_HOME files and browser localStorage into one JSON, imports it back after a per-file preview, and can run pnpm install to reinstall the listed plugins; the format is interchangeable with the dsh-market profile backup.

Staleness keeper for the Codebase Memory knowledge graph: it compares the graph Branch node head_sha with git rev-parse HEAD and reports an exact behindBy, rebuilds only the stale projects through the codebase-memory-mcp CLI so the MCP tool 60-second cap does not apply, watches each project for edits, and mirrors the same state into a settings card and a REST control surface.

Imports the MCP servers Codex and Claude Code already declare as dsh mcp-client tools, links the skills of 22 known agent skill directories into ~/.dsh/skills as symlinks instead of copying them, and adds a Settings page that lists what was mounted, toggles each skill, and changes the source on a name conflict.