Plugins

QA project workbench for dsh: manage test projects, requirements, test cases, defects, milestones, reports and approval gates through a browser UI and 18 QA-domain tools.

Twenty-one official HyperFrames by HeyGen skills synced from the official upstream (HTML video authoring, animation, keyframes, audio/music-to-video, CLI, registry, slideshow, talking-head recut, website/product/PR-to-video, Studio timeline conventions and more), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

DSH Web UI little whale-maid theme with light and dark palettes, ocean illustrations, hand-drawn frames, decorative assets, and a new built-in Codex-style pet.

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

Desktop notification reminders.

Personal agents with persistent memory, multi-Bot group collaboration and native background tasks for DeepSeek Harness.

A persistent AI companion for DSH that explores Bilibili, interacts with permission controls, and grows through evidence-backed life memories, evolving interests, simulated emotions, social relationships, and autonomous to-dos.

Lets the primary model ask an independent reviewer model to review a decision it has already made, with off, shadow and advisory modes. Requires your own service implementing POST /v1/decision.

Adds a switch between DeepSeek web chat and the Harness workspace in DSH Desktop.

Feishu/Lark bridge for local coding agents — one group, one conversation, one pinned runtime. Bridges dsh, CLI agents (traex/codex), an IDE window, or a custom agent behind one gateway.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

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.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

In-app plugin marketplace for DSH: plugin discovery, install, upgrade, toggle and uninstall in one panel for Web and Desktop host profiles, pairing a community catalog of 4,000+ entries with customizable curated lists, plus eight agent tools and a standalone dshm CLI, without a marketplace server or account.

SillyTavern-compatible roleplay with character cards, presets, world books, and swipe branches that restore their continuations alongside native DSH conversations.

Honcho memory plugin by Plastic Labs: injects the user profile, session summary and relevant conclusions at session start, uploads each turn to Honcho in the background with secrets redacted, and adds honcho_search / honcho_chat / honcho_remember tools plus a /honcho status command; configured through the ~/.honcho/config.json shared with the other Honcho integrations, against hosted honcho.dev or a self-hosted instance.

Project memory for dsh with native task-system integration: session todos and file reads auto-condense into cross-session task records (task↔file links), so workflows are switchable and resumable without re-contextualizing. Read-time memory (no upfront scan): extracts code symbols, summarizes docs, and cross-links docs↔symbols; optional TS semantic enhancement (auto on when TS installed). Experience notes auto-dedup. Every recall includes a traceable citation. Pure JS, single dep, works out of the box, silent operation, zero overhead.

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.

Google Antigravity / Cloud Code Assist model provider with quota management and model selector.

Cross-device session sync for DeepSeek Harness — syncs sessions and settings between machines through git.

OpenCues for DeepSeek Harness — LLM word alternatives and `_`-gated blank fill-ins in the dsh composer.

Self-contained browser runtime: Playwright (chromium) + OpenCLI as plugin-local dependencies (global reuse fallback), exposes a `browser` service and 9 interactive browser tools.

Adaptive deep-research orchestrator built on the official workflow engine.