Plugins

Model visibility manager for DeepSeek Harness: hide or show any model in the conversation model selector from a dedicated settings page. Per-model switches, search, provider-level batch actions, reset-all. Zero intrusion - writes only its own hidden list, never the provider config; hiding a model in use never interrupts a running session.

A-share market dashboard: realtime quotes and indices, millisecond full-market search, market sentiment thermometer, candlestick K-line detail popups, watchlist, ETF/convertible-bond/LOF boards, screener, and a 7x24 aggregated news feed.

Message-level full-text search across DSH sessions via an FTS5 trigram index (user / assistant / steering / tool with per-kind filters), deduplicated results across fork/continued sessions, read-only context preview with auto-scroll to the focused message, one-click jump to the real session, and incremental/full index rebuild with health check; zh/en i18n follows the Host locale service.

Manages archived DSH chats with conversation search, restore, and confirmed safe permanent deletion.

Deep literature research agent as a Deepseek-Harness preset powered by Scopus API.

DeepSeek Harness 的 Tavily 搜索插件

DeepSeek Harness web-search/web-fetch provider bundle backed by any degoog instance

DeepSeek Harness plugin: a deployment deny list of filesystem roots the model may never touch - fences read, write, search, and shell tool calls at tools/pre-execute

MiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.

A source library for DeepSeek Harness: 72 feeds on an hourly timer, a reader with transcripts and translation, and a publisher that turns what it collects into a podcast, a digest, or a report

Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

Provides web search capability to DSH via Tavily API

MiMo (Xiaomi) tools as a DSH profile plugin: web search, image/audio/video understanding, ASR transcription, TTS, voice design and voice cloning — native agent tools with a Settings page for the API key.

A curated library of 186 frontend/UI design skills across 15 collections, with a human-readable index (INDEX.md) and a machine-readable, searchable manifest (SKILLS-MANIFEST.json) for agents.

DuckDuckGo web search and URL fetch tools for DeepSeek Harness, no API key required. Provides web_search (via ddgs) and web_fetch (via trafilatura) as a drop-in bundle

Backs the native web_search and web_fetch tools with your self-hosted SearXNG instance, keyless and private.

Provider-neutral search and extraction tools for DeepSeek Harness

Bridges the MemOS memory service over MCP: the agent gets add/search/update/delete memory, multi-cube sharing, and a memory scheduler as mcp__memos__* tools.

LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.

DeepSeek Harness plugin: ingest research PDFs into a citable OKF markdown library, then search, graph, measure coverage, and write surveys in the same conversation

Multi-key Tavily search provider for DeepSeek Harness (ctx.web) with a live settings card in the web plugin configuration page

A self-contained second brain for DeepSeek Harness — auto-captures durable dialogue knowledge into a local Markdown vault (custom dedup, CJK search, git-friendly), with a graphical knowledge base and an interactive knowledge graph (legend filter, time-dimension coloring, box-select, merge, delete, PNG export/import).

Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.