Plugins

Multi-agent workflow for math-modeling contests: the "UltraMath" preset runs a problem from reading through framework, derivation, coding, verification, paper and review, plus 4 single-stage role presets (mathematician, engineer, writer, reviewer) and 33 model-library skill docs.

Let Your Ideas Flow — Tydora is a modern desktop Markdown editor combining WYSIWYG editing, bidirectional links, mind maps, and an infinite canvas — empowering deep thinking and effortless expression.

Research-only trading workbench bundle: typed market-data provider seam with a CSV reference provider, multi-timeframe indicator regime snapshot and OHLCV tools, interactive chart cards in dsh web with provenance-gated model annotations, and a risk-guard denying execution-shaped tool calls at tools/pre-execute.

Web access for DSH agents: fetch JS-rendered or protected pages as clean markdown, aggregated search across 14 engines, and stateful interactive sessions (click, type, scroll, eval, screenshot) against a hosted or self-hosted Rust browser engine. Every session returns a live view URL so a human can watch the agent browse and take over with the mouse.

Multi-model council for DeepSeek Harness: independent answers, anonymous peer reviews, and an inspectable final decision.

QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.

Lists the Markdown documents, images and video that already exist anywhere in the session workspace in the DSH sidebar, ranked by relevance to the current conversation: recent messages are matched locally against document title, summary and body with IDF weighting, with no model calls and no network. Because the list is scanned from the workspace instead of remembered, restarting DSH or starting a new session does not empty it. Images and video preview in place, with relative-path images resolved and video streamed over HTTP Range. A references bar under the preview header shows which documents cite the one being previewed and which it cites, with one click to jump between them. The same ranking is exposed to the agent as a knit_docs tool, which returns the most relevant documents along with the passage that matched in each, where one is found.

Tavern management panel for DeepSeek Harness: character cards, worldbooks and presets with per-session isolation, memory summaries, a character relationship web, one-click plot options and an NSFW mode. The full experience also needs the companion plugins dsh-muv-engine and dsh-muv-table, which render the status bar, the plot options and the variable tables.

A Blue Glass ocean-fantasy skin for DeepSeek Harness Web: crisp ocean backdrop, glass bubbles, an ocean sidebar with a gold-gradient HARNESS wordmark and a bottom cartoon character, a whale settings button, and gradient model text.

Fills in the Web UI's missing IDE workbench: resizable chat / editor / files-and-Git columns in Conversation, multi-tab file editing with save and new-file, workspace Terminal, a file tree with name filter and open-in-external-editor, SCM (stage/commit/push/pull, branch switch, Git graph, inline diffs), a status bar, and git_* model tools.

Side-panel arcade: 18 offline mini-games to play while the model thinks.

Configure the contextWindow for models registered in dsh, so long sessions are no longer misjudged as context overflow.

Multi-character Galgame conversation view with separate character and reply-model selection, per-character affection, memory, dialogue history, and CG galleries, plus responses informed by task events across Harness sessions.

Syncs the wallpaper currently applied in Wallpaper Engine to the DSH Web UI background through a local bridge: preview/capture/full render modes, monitor lock, a wallpaper library panel for local and market content, focus lens with eye tracking, immersive mode, and a Windows app launcher that installs software from direct links or a cloud-drive share link and starts it with one click.

aginxbrowser plugin for DeepSeek Harness: fetch JS-rendered / Cloudflare-protected pages as clean markdown, aggregated web search (Baidu/Sogou/WeChat and 11 more), and indexed interactive sessions (click / type / scroll / eval / screenshot) against a host

Live2D desk pet overlay for the DSH web GUI: mirrors agent state (thinking, idle, error, done, awaiting approval) with motions and speech bubbles, per-part touch reactions, drag-to-dock, switchable personas, and custom models via URL or local path.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Windows plugin that swaps the host shell executor for Git for Windows bash across every agent mode, materializes Git Bash variants of the standard, minimal, PTC and Cordis presets (per-file sha256-marked, user edits preserved), and exposes a gitBash capability so companion presets pick Git Bash automatically; when dsh-better-sidebar is installed it also adopts that sidebar's terminal shell (UI tabs and the model-facing terminal_* tools) through its official settings seam.

TinyFish-backed web search provider for the built-in web_search tool: each search is one GET to the TinyFish Search API, no model call.

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.

VSCode Remote-SSH-style development for DSH — connect to HPC and servers over SSH, read and edit remote files in the built-in Files tab, auto-SSH terminal, remote workspaces with single-roundtrip reads and result caching, and 12 session-aware remote_ssh_* model tools.

Zero-cost access to 6 free large models. No registration, no recharge, 6 free models built-in, multi-key rotation and rate-limit backoff.

Pair a second model that passively reviews each turn and injects notes.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.