Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 2479
dsh-self-learn
jackheather/dsh-self-learn
Learn from Bilibili videos, web pages, local files and live streams: local ASR, on-screen OCR and extractive digests add up to about 1.5KB of text per source, so the model reads a summary instead of a full transcript.
dsh-team-toolkit (team-compact)
dreamperday/dsh-team-toolkit
Manual context compaction for DSH Agent Teams, adding a scoped compact_context tool and the /compact-agent command.
connectors (deepseek-harness)
dotv-ai/connectors
Drive the DOTV infinite canvas from DeepSeek Harness: the agent lists your canvases and their nodes, adds text nodes, and runs image/video/audio generations — over DOTV's public API, with no runtime dependencies and no build step. It reuses the `dotv` CLI login on the machine, or takes an API key in the plugin settings. Generations consume credits on your account, exactly as they do in the app.
companion-memory
1326007879-sys/companion-memory
Local long-term memory core for DeepSeek Harness with plain-text notes, a bounded index, five tools, optional host-model consolidation and auditable evidence. It appends every user and assistant message under 32,000 characters to ~/.companion/cold/<date>.jsonl in plain text, with no built-in cleanup, and adds a short index of its notes to every system prompt; the optional model-based consolidation is off by default and, once on, sends those messages to the session's model.
dsh-compaction-vcc
tingfeng-droid/dsh-compaction-vcc
Replaces LLM summarization with deterministic text compilation, so compaction makes no model calls and keeps original tokens; elided content stays retrievable through seq pointers. Based on TsFreddie/dsh-compaction-instant.
dsh-qa-isolation
shadowtang98/dsh-qa-isolation
Adds a Q&A agent preset that answers each new question from a clean context: earlier exchanges leave the model input via a surface replacement, with no extra model call and no summary residue. A /qa follow command and a composer toggle switch to follow-up mode, and /clear archives the session and opens a fresh one under the same preset.
dsh-session-media
ok541151/dsh-session-media
Recovers the images and documents your past sessions carried: find attachments by topic across every stored session, get the original file path, or copy them out in one call. A context compressor only shrinks what is already inside the live window, and a transcript searcher returns quoted text, so neither hands back the original file. It also injects one per-workspace Markdown memory file into the system prompt every turn, searches past transcripts with AND keywords plus an optional time window and workspace filter, and reports index health. Keyword search only, no embedding service.
billion-context-patched
no-ni/billion-context-patched
A patched build of ranxianglei/billion-context (MIT) with the author's model-request accelerator folded in: verified snapshot reuse, parent-session inheritance for forks, outbound request-body compression, and image folding after the first send.
dsh-context-bridge
nevercanner/dsh-context-bridge
Manual session handoff: when you decide a session has run out of usable context, one click turns its event log into a compact handoff document (goal, done, next, project facts), creates a new session seeded with it and wakes it to continue; the new session can inherit the session-bus name as <name>-handoff. No threshold, no timer, no automatic trigger.
dsh-session-fold
kennethfan/dsh-session-fold
Folds older oversized tool results into spill files and replaces them with short, deterministic stubs at step boundaries, with no LLM call: the stub keeps the first 200 and last 80 characters plus the sequence number, tool name, line/char/size counts and the original file path, and each fold is a real surface replacement accompanied by compaction/prune shadow pricing so token counts stay honest. Triggers on context pressure at 25% of the model window (falling back to 32768 tokens when the window cannot be resolved) or on five accumulated candidates; the last three turns, error results and rich content are never folded. The original is recovered from the session log rather than the spill file, so /folds, /unfold <seq> and /unfold all keep working after spill cleanup; session_fold_recall lets the model fetch a folded result by sequence number or by keyword, and session_fold_diagnose reports the effective settings. /spill-prune removes orphaned spill directories, preview only unless --apply. A Settings page exposes 12 of the 13 options as draft-then-save fields; they are volatile, so saved changes apply without restarting the plugin.
dsh-context-domains
guicaiyue/dsh-context-domains
Puts a domain bar under the session header — a domain groups skills and tools and toggles as one block, so one click loads or unloads every member. Hovering a chip lists its members (skills, then tools) in a height-capped panel that scrolls. The right end of the bar is a compaction-threshold counter (− 5 +, 100k tokens per step) that rewrites the live compaction engine policies, so the compaction trigger line changes on the next turn without restarting dsh; a degraded fallback turns the number amber and is reported in the snapshot. Settings maintains domains and members with search, skill/tool tabs, all/selected/unselected filters and a copyable AI grouping prompt. Tool removal uses tools.restrict plus a guard; hiding a skill re-registers it with modelInvocable false, so it leaves the model catalog while /name still works. Sessions of another preset are left untouched.
dsh-plugins (archive-rsi)
feahter/dsh-plugins
Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.
dsh-message-cite
coraxeldridge/dsh-message-cite
Cites one specific message from another conversation: the @ menu inserts a chip, and at send time the quoted text is injected as untrusted background; a conversation_history tool also lets the model search and read other sessions of the same workspace. The @ menu searches the indexed sessions of every workspace (only the model tool is limited to the current one), and its HTTP routes (/dsh-message-cite/api/…) are guarded only by a marker header, not by a DSH access check.
dsh-qwenwork-models
sanmumu-325/dsh-qwenwork-models
Exposes the chat models of a locally signed-in QwenWork desktop app as a Harness provider, with a multi-account pool, session affinity and failover, pre-expiry credential renewal, a health watchdog, per-model enable/context-window/input-type settings, and account status with credit balance. Unofficial local integration that reuses your own signed-in client credential; your own account only. Windows only: needs the QwenWork desktop app signed in, and keeps its account pool in a DPAPI-protected file under %LOCALAPPDATA%. The author warns that reusing the client credential may conflict with the vendor's terms.
dsh-context-usage-for-agent
dixiewithheart/dsh-context-usage-for-agent
Gives the agent its own context usage through a context_usage tool plus one reading line per turn, with an editable template.
dsh-chat-wallpaper
yuxiangwhn/dsh-chat-wallpaper
Image wallpaper behind the DSH chat UI: the composer card, the user's own bubbles and the new-chat button become frosted glass, the blur deepens by 5px once the composer has text or the conversation already has messages, and a settings-style window frosts the whole backdrop while it stays sharp itself.
dsh-global-launcher
william-jin-cmu/dsh-global-launcher
A macOS global hotkey that opens a small prompt bar from any app and sends what you type, with an optional screenshot or window text, to a new or the last session.
dsh-bookmark
vaisramana/dsh-bookmark
Select text or tables in conversations to bookmark, highlight, and annotate in the right sidebar, with a collapsible all-sessions bookmark page.
DSH-Translate
light-cheng/dsh-translate
Bilingual reasoning, selection translation, composer polish, an offline English–Chinese dictionary with IPA, pronunciation and a vocabulary notebook for DeepSeek Harness. Instant selection translation is on by default and, on the cloud engine, sends the selected text to the model; pronunciation audio is fetched from Youdao when clicked or hovered; the bundled dictionary data (ECDICT and ipa-dict) is GPL-3.0.
dsh-plugins (mind-canvas)
feahter/dsh-plugins
Infinite-canvas mind map in the sidebar: grow nodes with Tab, tidy a branch into a tree, ask the assistant to expand a node into child ideas, and export to Markdown, OPML, FreeMind, JSON or PNG.
dsh-model-quick-selector
arrosam/dsh-model-quick-selector
Adds a quick-select model list to the DSH composer model button: a settings icon on the Model row of the model menu opens a dialog to pick and reorder favourite models, dragging vertically on the model button switches between them on release, and dragging left or right steps the reasoning effort; the menu's reasoning-effort row also gets a draggable slider (based on Microqian2th/dsh-codex-effort-slider). Text follows the DSH language setting (English / Chinese).
dsh-chinese-thinking-mode
qiao-fang/dsh-chinese-thinking-mode
Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.
dsh-wash
wwznm0/dsh-wash
会话净化:扫描本地会话记录,剥掉被模型抄进回复里的输入信封(<user_message>/<turn_meta>),备份后重写,可一键还原。
dsh-asc-studio
xdx888999/dsh-asc-studio
Edit App Store Connect listing text and images in the DeepSeek Harness sidebar.