Plugins

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

In-app DSH plugin marketplace panel with curated and full catalogs, keyword and semantic search, Chinese translation, favorites, installed-state tracking, and install/update/uninstall via the official CLI.

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.

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

Zhihu (知乎) dashboard: hot list with trend arrows, follow feed (favorites/creations/followees), post tracking (question/keyword/person) with auto-briefs, and five agent tools (zhihu_search/hot/answer/global_search/followees).

Use your ChatGPT/Codex subscriptions in DSH, with image generation and web search support.

Codex-style auto-hiding right-edge turn rail: edge-peek show/hide, per-turn tooltip, in-rail search, and a scrolling 30-turn window for long sessions.

DeepSeek Harness plugin market - browse, search & install dsh-plugin topic plugins (dsh 插件市场：浏览/搜索/安装插件)

Browse and search GitHub dsh-plugin repositories from Web UI Settings, sort by stars, and install plugins through the DSH CLI.

Native Search1API (s1) web research tools: search, news, page crawling, sitemap discovery, and trending topics as first-class `s1_*` tools, with a bundled s1 skill.

Multi-engine reverse image search aggregator: Google Lens, Baidu, Yandex, TinEye, SauceNAO, IQDB, Ascii2d.

Seed dsh plugin-market index sources on startup, so the Discover tab can search and install community plugins right after the bundle is installed.

Read-only Git graph tab for the DSH right sidebar — colored branch/merge lanes, HEAD / branch / tag / remote badges, commit details with a changed-file tree and per-file diff, virtualized rows that page through large histories — plus a branch chip in the composer that searches local and remote branches and switches with guards against uncommitted changes, detached worktrees and in-progress merges or rebases.

Read Zotero PDFs inside the DSH right sidebar and let the model work on them directly. Requires Zotero 10 or newer with the local API enabled (Zotero 7/8 is read-only and cannot accept annotations). The model gets three tools: search_zotero_library to search your library, read_zotero_paper to read a paper by page or by query, and ask_zotero_paper for page-cited answers. Annotation handling mirrors Zotero's own reader: click an annotation to open a card with page number, quoted text, a comment box and tags; the three-dot menu recolors or deletes it; multi-line selections get a single surrounding box rather than one box per line. Comments, tags, colors and deletions are written back through the Zotero local API, so they show up in Zotero and annotations made in Zotero show up here. Selection actions cover translate, explain, ask and highlight; the reader remembers the exact reading position (page plus offset) and zoom level per paper, and keeps opened PDFs mounted so switching tabs does not reload them. MinerU re-parsing is available for scanned or broken-text PDFs and is off by default.

Tag manager for DSH: create, search and delete tags, with soft-delete and per-item mappings used by the workbench task, site and storage plugins.

Chinese tax and cross-border e-commerce workbench: a local BigInt statement parser for Amazon, TikTok Shop, and Stripe CSV/TSV/XLSX exports (fintax_parse_statement), a 7-scenario deterministic tax and reconciliation calculator (fintax_calc), 4 read-only Tencent IMA knowledge-base tools (ima_list_kbs, ima_browse, ima_search, ima_read), 4 bundled compliance skills, and an in-app settings section. Statement files are parsed locally; optional IMA credentials are read from environment variables or ~/.config/ima/ (write-only via authenticated /api/fintax routes, never echoed back) and sent only to ima.qq.com; zero runtime dependencies.

Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.

Read and write your Obsidian vault from any conversation in DeepSeek Harness: daily notes, project notes, full-text search, and task check-off.

AlertManager panel in the DSH sidebar: reads multiple AlertManager HTTP API v2 instances in parallel, aggregates their alerts into severity-colored cards filterable by search, state, severity and instance, and dispatches any selection into a new session in a chosen workspace; the instance-grouped alerts become the first message to the agent, which then starts handling them immediately. Supports per-instance auth and TLS, auto-refresh, and a configurable dispatch prompt.

Interview coach with resume-grounded mock practice, deep dive, answer review, searchable answer library, and an evidence-first interviewer workspace.

A skill picker beside the composer that lists installed skills under Chinese categories, searches them by name or purpose, and suggests up to three skills matching the draft you are typing.

DokuWiki integration for DeepSeek Harness: native tools to read, search, write and delete wiki pages and upload media files, with ACL-aware tool exposure and credentials stored by DSH.

Native DSH support for context-mode (mksglu/context-mode), intercepting large tool outputs with SQLite FTS5 indexing, BM25+RRF search, and session continuity. On by default: tool outputs over 4 KB are replaced with a short preview while the full text is indexed into ~/.context-mode/context.db, and a section is added to the system prompt. Its ctx_execute and ctx_batch tools run shell, Node, Python, PowerShell or cmd commands with DSH's own permissions and environment (not sandboxed), and ctx_index reads any local file path or fetches any http(s) URL it is given.

Long-term memory for DSH where an LLM decides what to keep: turns pool while the session is idle, then the main chat model distills them into one-line entries in a single batched call; vector dedup runs before insert, so near-duplicates and saturated topics are dropped; recall uses hybrid vector plus FTS5 search over tiered hot, warm and cold storage; ships remember, recall, forget and prune tools. Zero dependencies, Node only.