Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

1742 plugins found

G

deepseek-harness-tui

gxinxing/deepseek-harness-tui

Terminal-native interactive TUI for DeepSeek Harness (dsh) — built with Ink, React for terminals

73 months agoDev & Plugin ToolsMIT
L

dsh-whale-animation

leemancheung/dsh-whale-animation

A 60-frame theme-aware monochrome whale-dive animation with reactive water for the DSH Web turn status: embedded assets, seamless closed-loop playback, a reduced-motion PNG fallback, and lifecycle-clean removal.

72 months agoUI EnhancementsMIT
M

dsh-plugin (dsh-bug-perf)

mzzsfy/dsh-plugin

Runtime workarounds for host defects while upstream fixes land: coalesce repeated session/follow rebuilds, reconnect a terminal view whose output stalled, keep the session stream alive when a proxy idles it out, cap job/list subscriptions, recover a session stuck on load, trim the session-list projection on the host and shrink the first-screen history window. Each feature has its own switch; when the host structure does not match, that feature is skipped, logging the reason or degrading silently.

63 days agoDev & Plugin ToolsMIT
W

dsh-split-view

weiaisuyan/dsh-split-view

Multi-column tabbed workspace for the DSH main area: up to four sessions side by side, each with its own tab strip, composer and host view switcher. Cannot be enabled together with luckybilly's dsh-split-view; installs as the package dsh-multipane.

64 days agoUI EnhancementsMIT
A

dsh-talent-tree

a961282799-crypto/dsh-talent-tree

A learning talent tree: give it a topic and the agent splits it into a prerequisite graph of knowledge points, each with a hook (the one formula, idea or question that makes it interesting), a plain-language summary and a symbol glossary; a point lights up bronze, silver or gold only after you explain it in your own words or answer a check question correctly. Adds a left-sidebar overview of every goal, a pannable and zoomable tree with learning routes and a recommended next point, a skip-ahead challenge, a due-review queue, light-up animations, KaTeX-rendered formulas and PNG export.

612 days agoTools & CapabilitiesMIT
Y

dsh-rtk-workbench

yunaaloft/dsh-rtk-workbench

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

67 days agoDev & Plugin ToolsApache-2.0
M

dsh-company

makooslee/dsh-company

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

64 days agoWorkflow & AutomationMIT
Y

dsh-free-model

ypipaq/dsh-free-model

dsh 插件(DeepSeek Harness / cordis bundle)· 模型接入 —— 把 CodeArts、CodeBuddy / WorkBuddy、LobsterAI、Qoder / Qoder CN、TRAE、Cline、Loomy、Raccoon、MiniMax Code、ZCode、Gemini、OfficeAce、Accio Work 十五个账号渠道接进 dsh 的模型选择器,并保留数据看板、运行日志与本地网关(含局域网中继)。上游 2.1.0 的匿名免费车道、EAC 协付车道、

6last monthModels & ProvidersMIT
B

dsh-aha-tutor

baroncyrus/dsh-aha-tutor

开窍 Aha Tutor: a personal AI tutor for DeepSeek Harness that builds a course around you and teaches it on a narrated handwriting whiteboard

627 days agoTools & CapabilitiesMIT
S

dsh-hindsight-local

snakejohn/dsh-hindsight-local

Long-term memory for dsh via a local Hindsight service: each turn is retained with local timestamps and relevant memories (time-aware, reranked) are recalled into context before replies; each workspace binds to one memory bank, several workspaces can share a bank, and banks can have Chinese names; what gets retained is configurable (default: user messages and AI replies); history is imported only when you choose to; includes a three-step setup page with one-click local deployment (uv + Python 3.12), a sidebar status card and a panel to browse and search memories. Needs a SiliconFlow API key for the default embedding and reranker models; only Linux is verified so far.

611 days agoMemoryMIT
K

dsh-threads

kyf-eng/dsh-threads

Claude-style projects and threads: a project's main conversation opens threads (real sessions you can open and talk to) for self-contained tasks, runs up to 3 at once by default, optionally each in its own git worktree, and gets each thread's report back.

612 days agoSessions & MessagesMIT
D

dsh-help-me-to-ask

doreihime/dsh-help-me-to-ask

On the first real work message of each chat window, asks for the missing goal, deliverable, constraints and acceptance criteria, then turns the answers into a short task sheet and injects it into the chat. Pure greetings are ignored.

627 days agoMemoryMIT
O

dsh-mobile

orderg-x/dsh-mobile

Use DSH from a phone browser. Turn on phone access from the phone button in the session header (or the plugin card) and scan the QR code; the phone opens the official DSH web UI served by the desktop process, with the same sessions updating live, so you can follow a running task, reply and approve away from the computer. A gateway inside DSH (port 18765) proxies the web UI and handles the desktop login itself. One QR code works on Wi-Fi and on mobile data: turning access on also starts a free Cloudflare quick tunnel (cloudflared is downloaded from Cloudflare's GitHub releases if missing), and its address survives DSH restarts, so phones do not need to rescan. Pairing codes are one-time and expire in 10 minutes, each phone gets its own revocable credential, the header button shows when a phone is connected, and idle connections get keepalive pings. Optional push notifications go to Bark, ntfy, ServerChan, Feishu / WeCom / DingTalk group bots, Telegram or any webhook when a task finishes (after 30 seconds or more), stops with an error, or waits for an approval or an answer; they carry only the session title and status, and approval still happens in DSH. On a phone the web UI's side panels slide over the page, and it can be added to the home screen with its own icon.

610 days agoIntegrations & RemoteMIT
W

dsh-status-bar (dsh-status-bar)

wfz2006/dsh-status-bar

Floating glass status bar for DSH on Windows 11 x64: an always-on-top capsule that mirrors session progress, the current step and pending approvals from a local DSH web profile, with peek and detail views; approval cards stay read-only until DSH returns its own decision receipt, and connecting to the official Desktop app is experimental and unverified.

63 days agoUI EnhancementsMIT
1

dsh-prompt-ErrorNotes-desk

1015677515/dsh-prompt-errornotes-desk

Captures the agent's own self-reported mistakes into a categorised lesson library that is re-injected into the system prompt every turn (each captured draft is confirmed or edited by the user before it is recorded), and adds two conversation-header panels for editing the cross-conversation global prompt and a per-session prompt.

619 days agoMemoryMIT
P

dsh-sensenova-pool

phoeky/dsh-sensenova-pool

Brings SenseNova (日日新) models into dsh with a per-key rotation pool: paste any number of API keys and requests rotate across them, a 429 rate-limit immediately retries on the next key with per-key exponential-backoff cooldown, local RPM pre-throttling avoids the limit instead of reacting to it, and an exhausted pool answers 503 with Retry-After so a 429 never reaches the caller. Ships a built-in model catalogue that works offline and refreshes from /v1/models, plus a settings card with masked keys, per-key probing and removal.

63 days agoModels & Providers
O

dsh-git-forge

omsociety/dsh-git-forge

Project-scoped Git credentials: forge accounts (GitHub, Gitea, GitLab, Bitbucket or a custom host) live in the right-sidebar "Git Forge" tab, are granted per project, and reach the agent as an HTTPS credential helper so the token never enters the conversation. Pushes to a host the project has not granted are rejected.

67 days agoGit & Code ReviewMIT
7

dsh-fact-check

7starsseeker/dsh-fact-check

Skill that types the request before it searches: it splits a question into premises, definitions and analysis units, decides which report skeleton fits (verdict, explainer, causal mechanism, comparison, survey map, metric card), confirms the direction and runs a feasibility check, then emits that skeleton instead of forcing every question into a true-false verdict — in Chinese or English. Evidence gathering never trusts model memory: it searches domestic and international ecosystems in parallel, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster, food safety, science, education, sports, entertainment, judicial, and more), fetches primary pages, grades sources by type, re-searches with debunking keywords, and keeps every statement bound to a full URL and citation position. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

63 days agoSkillsMIT
J

dsh-im-humanize

john-walks-slow/dsh-im-humanize

Humanized fork of @xmanrui/dsh-im (base 4.21.2): humanized message delivery with send-delay and typing two-phase, message_break + streaming coexistence, status reactions, reply quotes, per-bot humanize overrides, and a no_reply reclaim tool — across WeChat, Feishu, DingTalk, WeCom, QQ, Telegram, Slack and WhatsApp channels.

628 days agoIntegrations & RemoteMIT
M

dsh-plugin (dsh-auto-trust-all)

mzzsfy/dsh-plugin

Makes every Host header that actually reaches the server a trusted entry: all webServer routes are wrapped and the parsed host is registered in connection.trustedHosts (mirrored into webRuntime.trustedHosts on host generations that still have that service), so wildcard or otherwise unenumerable entry domains work without editing the start command; entries beyond a configurable capacity are evicted LRU-first. It does not change the listen binding — that stays with the deployment layer — and the authentication layer is untouched. Because any Host header is accepted, the host allowlist no longer protects against DNS rebinding; use it only on a network you trust.

63 days agoIntegrations & RemoteMIT
M

dsh-plugin (dsh-turn-notify)

mzzsfy/dsh-plugin

Turn event notifications: six event classes (completed, error, interrupted, approval requested, AI question, limit reached) delivered via sound, system notification, in-page banner, webhook, IM and host desktop-notification channels; when several browser windows are open, only one rings.

63 days agoIntegrations & RemoteMIT
E

web-clone

edisonzszs/web-clone

Website cloning methodology skill: a real-source-first decision tree covering static sites, React/Vue/Next content sites and WebGL/Canvas-heavy fronts, mandatory verification of executable code quoted from second-hand AI analyses, and 13 zero-dependency Node scripts for CDP browser recon, asset/font harvesting, route crawling, sourcemap hunting and pixel-diff auditing.

62 months agoSkillsMIT
B

dsh-custom-mode (editor)

bowluna/dsh-custom-mode

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

62 months agoIntegrations & RemoteMIT
F

dsh-composer-ux

fangwen9527/dsh-composer-ux

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

69 days agoUI EnhancementsMIT