Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 1010
dsh-fun-waiting
jackyhuang75414/dsh-fun-waiting
Replaces the chat's "Deep diving" waiting label with rotating fun phrases, editable live in Settings.
dsh-qq-waifu
daphne999/dsh-qq-waifu
Waifu mode for QQ: splits every reply into several short chat bubbles with a human-like typing delay, drops trailing periods, and keeps tables and code blocks intact. Works by patching @tencent-connect/dsh-qqbot in the desktop profile: run node outbound/apply-patch.mjs once, set im-qqbot streaming: false, then restart — until then only the waifu_* tools work.
dsh-wenjian-team
sarsgy-wenjian/dsh-wenjian-team
Long-form manuscript verification team for DSH: installs 10 skills that run a read-only content/structure check, three-tier revision proposals, a human-selection gate, exact replacements and a final re-check; it never edits the manuscript by itself and requires Agent Teams to spawn teammates.
dsh-wechat-todo
pythoner1984/dsh-wechat-todo
Turns your local WeChat group chats into a followable todo board: a three-column kanban (todo / doing / needs you) with LLM summaries, automatic flagging of messages that @-mention or reply to you, drag-to-change status, and local-only storage. Needs a local Python 3 with sqlcipher3 and zstandard, plus the existing rion-wechat-reader config.json and keys.json for the WeChat databases; the plugin does not extract the keys itself, and summaries send the quoted chat text to the model you choose.
dsh-feiyu-affinity
xxgj666/dsh-feiyu-affinity
Per-person affinity for DSH personas on a QQ channel (a QQ bridge such as dsh-onebot-qq is required — the person is identified by the QQ number in each message; on the plain web UI nothing is injected): per-user scores with daily decay, reasons history, sulking and forgiveness, plus a global mood that colors replies.
dsh-nitro
clockclock1/dsh-nitro
Per-session fast-delivery mode from the composer. New conversations start enabled; switching is refused while that conversation is running, and a read-only session-header badge shows on/off during a run. One switch drives three subsystems: a circuit breaker that short-circuits test and build commands instead of running them, an apply_patch tool that writes SEARCH/REPLACE hunks atomically (all anchors must match or nothing is written), and a dehydrator that trims terminal output to a pass line or the last 15 error lines.
dsh-ming-graph
chess12333/dsh-ming-graph
A graph of your memory store for DSH: one node per real memory, and every edge must state why the two are connected — a quoted keyword, a shared term, a project, or temporal adjacency. Pure filesystem reads with no model in the loop; unreadable sources are reported, never replaced with fake nodes.
dsh-strata
light-cheng/dsh-strata
Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.
dsh-stuck-monitor
jwang513/dsh-stuck-monitor
Passive recorder that replays the main agent and every subagent on one timeline, flags repeated calls, loops, recurring errors and truncated output, and writes an AI cause-and-effect review on demand.
dsh-tlpro-models
dungcsnd1133/dsh-tlpro-models
Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.
dsh-memory-router
dcd887/dsh-memory-router
Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.
dsh-codex-kit (projects-browser)
xchcy/dsh-codex-kit
Replaces the sidebar workspace list with a Codex-style browser: sticky Pinned / Projects / Recent sections, status marks for working, awaiting approval, interrupted, and completed sessions, right-click sorting plus workspace rename and delete, and per-session pin and archive menus.
dsh-desktop-restart-button
jh0oo/dsh-desktop-restart-button
Adds a restart button to the Windows desktop app title bar and replaces the cold-start "loading settings" overlay with an animated boot sequence.
dsh-chat-lanes
hellmage/dsh-chat-lanes
Splits the DSH chat window into two columns: your messages pinned in a clickable left rail and the model replies flowing on the right, with Enter-to-search across the conversation.
dsh-dl-brand
dungcsnd1133/dsh-dl-brand
Replaces the sidebar brand mark with a custom one and registers a Vietnamese locale covering 45 namespaces and 1897 interface strings, falling back to English for anything untranslated.
dsh-assistant
starsharryzhu/dsh-assistant
General-purpose chat agent on a parent agent + worker sub-agent split, for DSH Desktop only: a sidebar row opens each assistant's long-running conversation, where the parent chats, records schedule, lists, memos, logs, profile, persona and projects as plain files in that assistant's workspace folder, and hands other work to background workers through the bundled complete-subagent, picking each worker's model from the ones you enable and approving their write access. A heartbeat wakes it for reminders, a daily brief and wake-ups it sets itself, and holds back during quiet hours. Through the bundled im-robot it chats over WeChat: the model decides per reply with im_route whether the reply also goes to WeChat, and images and files sent from WeChat appear in the conversation and stay in the workspace's IM/WeChat folder for a set number of days. Its tools never appear in normal sessions.
dsh-session-folders
yinqisy/dsh-session-folders
Groups sidebar conversations into collapsible folders that reorder by drag, decorating the shipped session list instead of replacing it.
dsh-agent-lab
limtide/dsh-agent-lab
Records a session as a run, replays it in an isolated workspace copy with another model or prompt, diffs the two trajectories side by side, aggregates runs into a task × variant matrix, and gates regressions with task assertions and a CI exit code.
dsh-mp4
shshjjj456/dsh-mp4
Plays MP4, M4V and MOV videos in the DSH right sidebar using the native video player, replacing the "this file type cannot be previewed" placeholder.
dsh-whale-tts
cilis/dsh-whale-tts
Provider-agnostic text-to-speech for DeepSeek Harness: synthesize speech to local audio files, manage preset, cloned and designed voices, configure providers in a bilingual settings card, and read assistant replies aloud with optional auto-read.
dsh-usage-replay
eclipse-notfound/dsh-usage-replay
Cross-session per-model token usage replayed from the harness's own session logs, with a usage panel tab (requires dsh-better-sidebar) and a per-conversation model popover.
dsh-add-to-chat
zoenghao-gif/dsh-add-to-chat
Right-click any selected assistant reply and add it to the composer as a removable quote chip. The selected text is delivered to the model as hidden context, so your message bubble keeps only your own words.
dsh-effort-slider
suyunxing/dsh-effort-slider
Replaces the composer's model selector with a starfield popup that sets the model and its reasoning effort in one control, and remaps the current effort to the nearest level the new model declares instead of failing the switch.
dsh-quote-reply
gf691271/dsh-quote-reply
Quote and reply the way Claude Code does it: select text, answer it in a popover, stack the pairs as blocks above the composer, send them as one message.