Plugins

Responsive MCP management UI for DeepSeek Harness Web — floating panel, JSON import, and profile-backed Host Remote management.

Display-layer translation for the DSH Web UI — thinking chains, task cards and answers in 8 target languages via local Ollama or Google/Bing, originals preserved.

Connects DeepSeek Harness to Multisim MCP for circuit generation, simulation, diagnostics, design optimization, and experiment report export.

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

AI 原生智能爬虫与 JavaScript 逆向工程平台，基于 DSH、Patchright/CDP 与独立语义运行时，从浏览器证据恢复参数生成逻辑并交付可验证 Solver。

DSH (DeepSeek Harness) 的 QQ2006 皮肤插件：注册 qq2006 主题、镜像 body[data-ds-skin]、全局皮肤表与完整素材

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

Save every repetitive, tiresome templated prompt — one mouse click injects it into the composer and spares you the effort. 🌹

ClearAI: The Epistemic Loop, native to DSH.

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

IM Companion for dsh-im: groups Feishu/WeChat/QQ bots by Agent in DSH workspaces and enhances DSH native session states (blue/orange/red rail markers for running, needs-review and error), with left badges, one-click filter, fleet overview and drag-to-move. Clean uninstall.

OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.

更好的右键：DeepSeek Harness 应用封装端的完整原生风格上下文菜单

NiuLai meme desktop pet — shouts "Ma～ma～" with a synced mouth when your agent finishes; 6 skins, signature actions, action-event binding, WebAudio-synthesized animal calls, hand-drawn SVG skins bundled.

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.

Modifies DSH plugin code at runtime, with ordered patches, inspection, and hot reload.

Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI and web login.

Animated mood icon: swaps the favicon, sidebar wordmark and hero headline for bloub expression animations that follow session state (working / awaiting input / done / idle), with 8 shapes, 12 colors and custom wordmark texts configurable in Settings.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Git worktree Session Targets with isolated task sessions, Ready for Review, reversible Local Preview, human-confirmed delivery, environment retention and recovery, and same-session iteration.

Particle-network background overlay for the DSH Web shell: full-screen, click-through, zero runtime dependencies.

Live-tune the DSH Web conversation UI from Settings: message font size, Claude Desktop-style markdown tables, dialog width, an optional timeline rail, and a GitBar with branch management, per-file diff, and commit & push.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.