Plugins

Un plugin de poste de travail scientifique reproductible pour DeepSeek Harness : cellules pilotées par l'agent, figures en ligne avec retour/réexécution, provenance par manifeste et instantanés d'environnement.

Extension d'assistant d'apprentissage pour DeepSeek Harness (dsh) : tutorat DeepTutor pour votre agent — explications approfondies, questions d'auto-évaluation, parcours d'apprentissage, recherche dans une base de connaissances personnelle (RAG) et archivage de notes (HTTP/WS en priorité, repli CLI ; s'adapte automatiquement au local/distant).

Découverte d'outils à la demande par agent et divulgation progressive des schémas.

Search AIGC Radar's curated GitHub AI project library (500-star admission, bilingual tags, star-growth snapshots) over its MCP endpoint with native result cards; a pre-step listener nudges a reuse check before the agent writes code.

Multi-provider web search for DeepSeek Harness: Baidu, Doubao, Tavily, and Exa backends for ctx.web.

pi-web-access for the DeepSeek Harness: multi-provider web search with automatic fallback (SearXNG → Tavily → Brave → keyless DuckDuckGo) plus URL content extraction, wired into the web seam so the built-in web_search tool is powered by piwa. Search engin

The research plugin market inside DeepSeek Harness: browse a curated index of literature, reference, writing and workbench plugins in Settings and install them with one click — 科研插件市场，在设置里浏览并一键安装。

Codex web search provider for DeepSeek Harness (DSH)

dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).

Modular search tool for DeepSeek Harness: attach SearXNG, RAG and your own sections to the native web_search.

Low-intrusion Settings presentation layer for DSH: group plugins, hide single settings / whole plugins, search settings, and restore hidden items — entirely through DSH's additive client-slot + settings-namespace seams.

DSH plugin: automatic dual-peer Honcho v3 memory, contextual recall, search, reasoning, conclusions, and health diagnostics

Turns a stated need into a plugin choice: an agent skill that queries a catalog of the whole `dsh-plugin` topic (2600+ repos, recrawled every 6 hours, Chinese descriptions from Workers AI) through a ranked search API, then hands back the matching `dsh plugin add` command.

A plugin market for DeepSeek Harness: search and one-click install GitHub dsh-plugin plugins straight from the web GUI.

Quality-aware in-agent plugin discovery: a find_dsh_plugins tool that ranks the whole dsh-plugin topic through a daily quality-scored index (installable manifest, curated listing, license, activity) merged with a live gh search — zero LLM API cost, risk flags and exact install commands in every result.

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

Connect dsh to Notion via the official Notion MCP (OAuth + PKCE): search, read, and write pages, databases, and comments through `mcp__notion__*` tools.

Minimal prompt x full PTC tools: one-line persona, Code Mode SDK, subagents, workflows, web search, and Windows Git Bash.

Metaso (秘塔AI搜索) search & reader providers for the web seam: web_search returns page summaries, web_fetch reads full-page markdown, multi-scope search (webpage/document/paper/image/video/podcast).

Firecrawl-backed web search provider for the built-in web_search tool, with a settings card for the API key and result limits.

Jira Cloud issue-tracker integration exposing eight model tools for issue search, project and transition lookup, creation, updates, comments, and transitions; writes are opt-in and support dry-run.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation and bounded-concurrency DOI validation.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

Qichacha (企查查) enterprise data source as a dynamic Cordis plugin: 5 agent tools (auth with QR login, company search, knowledge search, tool search, tool execute) covering 100+ data dimensions (business registration, shareholders, judicial, IP), plus a settings-page account manager; network/file IO via DSH subprocess spawning node -e, credentials interop with the local BizOwl client.