1704 results
Context Assembler DSH V0.99 — Context Assembler plugin for DeepSeek Harness (dsh): context compaction, cache-friendly topic-block management, water-pressure topic splitting, tool trace/rewrite, handoff planning and reality recall injection.
dsh plugin: complete Office document tools for the agent (create/read/edit .docx/.xlsx/.pptx through the OfficeCLI binary) plus a document preview in the dsh web sidebar via dsh-better-sidebar.
Coding-plan quota and balance readout for the DSH composer toolbar: MiniMax, DeepSeek, Kimi, OpenRouter and Zhipu windows follow the selected model; API keys are reused from DSH model settings.
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
Health checks for DeepSeek Harness: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + manifest-BOM detection, environment diagnostics, supply-chain poison preflight, and broken tool-call-sequence detection (#2334).
dsh bundle: register ywleeo/browser-mcp (a local MCP server driving a real Chrome to search, capture, and automate any logged-in site) as native dsh MCP tools (mcp__browser__*).
DSH 外部插件：模型在对话流中流式生成 SVG/HTML Widget（```svg/```html 围栏逐 token 渲染于沙箱 iframe）与结构化图表（visualize 工具的 ChartSpec -> echarts）。复用已有 assistant/chunk + tool/result 事件，不改 DSH 源码。
Desktop computer use for DeepSeek Harness (DSH): macOS app listing, accessibility-tree window capture, screenshots, and synthesized input — the seam, the local Swift-daemon provider, the computer_use_* tools, the approval policy, and a standalone MCP server in one installable plugin package
DeepSeek Harness pet companion — Codex Pets style floating pet with notification broadcasting and a pet_say tool
古法编程：在 DSH Web UI 中提供 Monaco 编辑器 + 文件树覆盖层面板
Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScript sources, built with tsc + esbuild.
Nested (tree-shaped) todo tool for DeepSeek Harness: registers todo_tree_write alongside the flat dsh-tool-todo
DSH host plugin that detects when the DeepSeek Harness service has restarted and wakes the main agent at boot with a notice, so interrupted work can be resumed.
Obsidian side-panel math memory agent for DeepSeek Harness: layered long-term memory, idea memo with proactive review reminders, unified note_recall retrieval plus dedicated note search/create/backlink tools. Ships as both a dsh plugin and an Obsidian community plugin.
Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.
The single plugin you need for DSH
Laya typed decisions (noul / choice / score) as a first-class Cordis service and model-visible tools for DeepSeek Harness.
Volcengine Ark Managed Agents plugin for DeepSeek Harness (DSH): a Managed Agents settings tab plus tools to dispatch tasks to Ark cloud Managed Agents and retrieve their trajectory, result, and artifacts.
Composer draft polisher for DeepSeek Harness: a ✨ button in the composer tool row rewrites the current draft with a zero-prefix flash call and fills the polished text straight back into the input box.
ChangeProof - change-relevance + evidence-freshness quality plugin for DeepSeek Harness (DSH)
DSH Web plugin that lets text-only models see images: paste images in the chat and send without file paths; the model discovers its own vision tools. Multimodal models pass through natively.
DeepSeek Harness plugin (Cordis toolset) for reading, searching, and editing a local Obsidian vault, with optional Local REST API integration.
DSH Longbridge (长桥) HK/US market plugin: quotes, account, positions and order tools plus a settings surface
Tool search & slimming for DeepSeek Harness: Hermes-style progressive disclosure — search, describe, and call long-tail tools on demand while keeping core tools eager