dsh-kokoro
DeepSeek Harness plugin: speak text with a local Kokoro TTS HTTP server and return the wav path, as the kokoro_tts tool. Ships no weights.
896 results
DeepSeek Harness plugin: speak text with a local Kokoro TTS HTTP server and return the wav path, as the kokoro_tts tool. Ships no weights.
Idle-triggered context compaction for DeepSeek Harness: compact a session once it has gone quiet past a token floor
Fix the DeepSeek Harness Web GUI over plain HTTP on a LAN: injects a crypto.randomUUID polyfill (getRandomValues-backed) before dsh bundle code runs. No official source changes needed.
MCP client hub (stdio / Streamable HTTP / SSE) with skill, command, memory and prompt management for the DeepSeek Harness Web GUI
KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.
Structured context for DeepSeek Harness: split the conversation into typed sub-contexts (reasoning / tool calls / replies) and index them with a table of contents. 结构化 dsh 上下文:按类型拆分小上下文(思考/工具调用/正式回复),以结构化目录为索引。
DSH profile bundle: @-mention files and directories of the current session's workspace in the composer — prioritized fuzzy search, arrow-key/Tab completion, plain-text mentions that can be copied or edited, per-workspace indexing with LRU cache, and durable settings.
DSH web plugin that ranks OpenRouter upstream providers by quality, speed, cache-heavy price, context, and uptime, then safely switches the active route.
LongCat (LongCat-2.0) model provider for DeepSeek Harness — 1M context, thinking mode, tool calling
Auto-fold context/system messages in DSH conversation — hide the large system prompt / instructions by default, click to expand.
Memo — session memory search for DeepSeek Harness agents: cross-session full-text recall (memo_search), distilled notes (memo_remember), and corpus stats (memo_stats) over the official sessionQuery service. Zero infrastructure, local-first.
MiniMax 文生图插件:把一句话画面描述生成图片并保存到工作区,作为 `image-gen` 工具提供给模型调用。
The see tool for the DeepSeek Harness: offline OCR with positions (macOS Vision) + ASCII layout art (PIL) + vision-model semantic description (mimo-v2.5 via the opencode-go gateway). Works with any model, including text-only ones.
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts
Paper Plane X plugin for DeepSeek Harness Web: context panel + /ppx-paper search
OpenViking memory integration: Web Settings plugin card + automatic memory-context injection
Model-facing ocr_image tool that runs local RapidOCR (via a Python subprocess) and returns image text as plain text, so text-only DeepSeek models can read images
The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.
Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers
文本行去重/排序/统计
DeepSeek Harness plugin: drive the local Grok Build CLI for text, image, and video.
文本换行
Lightweight DSH upload bridge: images and common documents become workspace paths so a text-only DeepSeek model can read them with Qwen-MM-Plugins vision tools.
DSH WebUI 语音输入插件(火山引擎流式 ASR / 豆包 Seed ASR):输入框麦克风按钮(Alt+V)→ 浏览器采集 16kHz PCM → 经宿主 WebSocket 中继到豆包流式识别 → 实时回填(跟随光标/Proma 式输出,失败兜底剪贴板)。协议实现源自 Proma 桌面端调研复刻。