724 results
AI-for-Science research workflow skill bundle for DeepSeek Harness: multi-angle literature review with per-angle files, anchored experiment design with a caveat list, figures, paper reading; cross-verification briefs.
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
A general-purpose knowledge base plugin for DeepSeek Harness (DSH): import documents (md/txt/json/yml/docx/pdf), organize them in folders, and search with FTS5. 通用知识库插件：文件导入、目录化管理、全文检索、知识库管理 UI。
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.
Windows XP Luna desktop theme for the DeepSeek Harness web GUI: floating window manager with taskbar and desktop icons, Explorer-style workspace/session browser, native directory picker, search and the Luna token palette.
Modular AI research/engineering skill pack for DeepSeek Harness — security audit, paper workflows, dev workflow, storage analysis. Installable via dsh plugin add.
Question-Driven Discovery CLI
Multi-provider web search plugin for DeepSeek Harness supporting free-tier providers (Bing, Baidu, 360, Tavily, Brave, Serper, Bocha, SearXNG, DuckDuckGo) with auto-fallback and Web Settings UI.
dsh plugin: back the native web_search / web_fetch tools with your self-hosted SearXNG instance - keyless, private, no third-party search vendor.
CodeGraph for DSH — registers native `codegraph_*` tools (core surface: status/init/sync/explore; full surface adds query/node/files/callers/callees/impact/affected/index/uninit) wrapping the `codegraph` CLI, plus a prompt front-load hook that steers structural CodeGraph context into structural prompts, so the DSH agent can bootstrap, maintain, and query a pre-indexed code knowledge graph without grepping files.
dsh-skillport — every skill you already have (Claude Code, Codex, Cursor, Gemini CLI) works in DSH: Agent Skills SKILL.md discovery across .claude/.agents/.dsh/.gemini + extraPaths, Tier-2 conversions (cursor rules, claude commands, context files), find_skill search, and a skills doctor
OpenCode Zen provider adapter for DSH harness LLM seam
SearXNG-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
DeepSeek Harness 的 TencentDB Agent Memory 移植：L0 对话捕获 → L1 结构化记忆提取 → L2 场景/L3 画像，自动召回注入 + 记忆/对话搜索工具；复用现有 ~/.memory-tencentdb/memory-tdai 数据；附 Web UI 设置栏。
MCP 与技能管理面板：设置页展示 MCP 服务器与 Skill 目录，随时启停释放上下文占用；可选 AI 中间层（mcp_search/mcp_call）按需使用 MCP。
Search dsh.fish and install any harness artifact from inside your agent, authenticated with your hub account.
Zero-config Exa web search provider for DeepSeek Harness (dsh): keyless anonymous MCP fallback (mcp.exa.ai/mcp) plus keyed REST search — a drop-in WebSearchProvider for the ctx.web seam, no API key required.
DSH 免费网页搜索 provider + 设置开关（Parallel 默认 / Exa 备用）+ MCP server 双传输（stdio + HTTP/SSE），兼容 Claude Code / Codex，一键切换官方计费搜索与免费搜索
Xiaomi MiMo search + multimodal tools for DSH agents: mimo_search/vision/audio/video/asr/tts.
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__*).
Unified agent memory for DeepSeek Harness — one shared Obsidian vault for every agent (dsh, Codex, Claude, Hermes). Ships the dependency-free Python core (search/promote/adjudicate/forget), a vault template, and a dsh plugin with memory_search / memory_show / memory_submit / memory_status tools. · 统一 Agent 记忆系统：多 Agent 共享一个 Obsidian vault，附零依赖 Python core 与 dsh 插件。
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.
RigorQuant for DeepSeek Harness: session-scoped unattended, context-isolated multi-agent research for empirical/computational mathematics with a four-part pre-implementation check battery and a jacobian/Lean escalation lane.
A document-first reader profile bundle for DeepSeek Harness: curated, ordered, searchable, translatable reading of DSH's own documentation over dsh-base + dsh-web-app.