Plugins

Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.

Browser operation by accessibility refs: navigate, snapshot the page as a ref tree, act on elements, and wait for conditions; the origin policy follows the session approval stance and is enforced by request interception.

Real-browser automation for dsh via an MCP server (Playwright core): navigate, click, fill, type, screenshot, and act on accessibility snapshots with numbered references - all 22 web_* tools re-exposed to the harness over stdio.

Render Markdown + JSON into self-contained HTML documents, cards, dashboards, and galleries (CLI + artifact_render tool).

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

On-demand GitHub proxy for the Web UI: one-click git/SSH proxy toggle with connectivity tests.

MCP server manager (stdio / streamable-http): per-working-directory project and global config tiers; project-level MCP collapsed into 4 atomic tools through a middleware layer by default (`middleware: all` folds in global servers too, hot-switchable in the settings page); workspace isolation prevents cross-project interference; configs keep `${ENV}` references only, with no plaintext secrets on disk; runtime registration API for other plugins to inject MCP servers.

Turn any SVG logo into a motion video inside DSH: an `animate_svg` tool renders a transparent 30fps assembly animation (parts fly in, or the whole mark settles) and synthesizes an MP4 with ffmpeg.

Notes and todos as plain Markdown files in your workspace: type /ml plus a sentence to jot into today's journal; todos come in three flavors — deadline, sleep-until-a-date (auto-wakes when due), and anytime; /ml view fuzzy-opens any file with a few keystrokes. Zero tokens throughout — nothing goes through the model, and your notes stay ordinary local files that git and any editor can read.

Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.

PubMed deep-research toolset: literature search, author investigation, same-name disambiguation, institution statistics and mentor-student matching.

Zotero as an evidence store for agents: search your library, inspect metadata and notes, retrieve evidence passages, open source PDFs, and generate citations and bibliographies.