dsh-win-minimal
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
814 results
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
Thin on-demand context-retrieval layer for DeepSeek Harness: context_query / context_slice / context_grep tools over the sessionQuery and subprocess seams.
DSH plugin for semantic code search via Milvus vector database
Local IndexTTS 2.5 and GPT-SoVITS sentence-level speech synthesis and playback for DeepSeek Harness
Real-time weather, location, battery, and system-device context for DeepSeek Harness
Ask any line of code its backstory: what it does, and why it's here — grounded in git history and the agent's own session log. Ships a DeepSeek Harness plugin and a standalone MCP server.
Web page reader for DeepSeek Harness (dsh): fetch any URL and extract clean markdown or plain text, inventory links, read RSS/Atom feeds, and inspect HTTP headers without the body — zero runtime dependencies
DSH Web selection-annotation plugin: select assistant text, annotate (optional), and press Enter to send the annotation block with your message — the model replies to each annotation by number, with hoverable chips in the reply.
DingTalk Stream text, image, and file channel bridge for DeepSeek Harness
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
Let the model render an image into the DSH web chat flow (QQ/WeChat style) via a show_image tool: the message content keeps only the path text, the image never enters model context, and the browser shows the picture inline, scrollable with history.
Native DSH Settings → Usage page for DeepSeek API: balance, official token and cost analysis, trends, context warnings, and live API activity.
会话级自动上下文压缩插件:回合中每步前 + 回合结束检测上下文用量,超过会话阈值自动 compact,摘要注入上下文后自然继续(DeepSeek Harness / DSH)
Let DSH text-only-model conversations accept dragged/pasted images: save them into the session workspace and insert the file path as text, bypassing the webui attachment channel that otherwise rejects image parts.
给 DeepSeek Harness(DSH / DeepSeek Hermes)加语音能力的社区插件:输入框语音输入(可配快捷键)+ 回答朗读(微软 Edge 神经网络音色,可换音色、可试听),无需 API Key。
Vision sidecar for text-only coding agents.
DSH 记忆管理插件(宿主级,标准化重写版):文件夹记忆库、印象、组合与双向链接、会话级注入计划与消息注入、规约记忆与最近会话总结的新会话自动注入、会话总结、跨工作区会话列表、6 个 Agent 记忆工具、左侧图谱双视图浮层与消息跳转、设置页开关。只依赖 DSH 核心扩展点(settings/tools/agent 事件/webServer),功能实现自包含,官方升级影响面最小。
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
Cross-session memory cue bank for DeepSeek Harness: builds a persistent event-cue library (keywords, user language idiosyncrasies) and re-activates remembered event details on topic switches, mirroring human episodic recall.
Model-authored context pruning for DeepSeek Harness through the official compaction API.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva
Message edit / regenerate for DSH Web: inline edit of assistant replies (text + reasoning), regenerate replies, and user-message edit — a Cordis host plugin serving /api/msg-edit/* plus a dsh.client UI plugin contributing to the assistant action strip.