Plugins
Browse, filter, and install DeepSeek-Harness plugins.
2504 plugins found
dsh-discord
suuuuuu-1/dsh-discord
Discord-native remote controller for DeepSeek Harness: drive persisted coding-agent sessions from DMs, mention-gated guild channels, and threads, with slash commands, progress updates, approvals, structured questions, and image and text attachments.
dsh-plan-lattice
1052326311/dsh-plan-lattice
Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.
dsh-markdown-preview
githubjike/dsh-markdown-preview
In-chat preview for produced files: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.
voco-input-sh
nothree-code/voco-input-sh
Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).
dsh-stt-input
baisama-cloud/dsh-stt-input
Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.
dsh-vision-mix
haiziyao/dsh-vision-mix
Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.
dsh-devtoolbox
jean3690/dsh-devtoolbox
Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.
dsh-mcp-bridge
chhlafiu4312/dsh-mcp-bridge
Zero-dependency MCP client bridge that connects stdio and HTTP MCP servers and registers their tools as mcp_<server>_<tool> for the agent.
dsh-auto-compact
songoao25/dsh-auto-compact
Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.
dsh-ds-attach
wqx-txdsyl/dsh-ds-attach
**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.
dsh-pdf
sunshine-lang/dsh-pdf
PDF toolbox for DeepSeek Harness: extract text, metadata, and page ranges from PDF files (local parsing, no API key).
dsh-dingtalk
stardustlc666/dsh-dingtalk
DingTalk group-robot notifications (notify/text/health; webhook + HMAC signing, zero runtime dependencies).
qiushi-dsh-evidence-audit
030611/qiushi-dsh-evidence-audit
Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.
dsh-session-audit
bwndlct/dsh-session-audit
Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.
dsh-voice
jesse-njx/dsh-voice
Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.
deepseek-heartflow
yun520-1/deepseek-heartflow
HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.
dsh-llm-vision-bridge
einskyle/dsh-llm-vision-bridge
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
dsh-plain-memory
simin-yuan/dsh-plain-memory
Plain-text memory for DeepSeek Harness: Markdown in your own Git repo, a self layer loaded into AGENTS.md at session start, cross-window recall, zero injection and zero model calls by default.
openseek-lcm
pub-polaris/openseek-lcm
Lossless Context Memory for DeepSeek Harness: archives older session context outside the active prompt and recalls what the current turn needs.
Aesthetics-OS
greatbeing/aesthetics-os
Bundles the Aesthetics-OS aesthetic-judgment skill as a runtime skill with a red-line routing section, plus 22 native tools backed by bundled Python scripts: a persistent propose→brief→evidence→measure→critique→verdict state machine that refuses unverified passes, a delivery gate, fingerprint-based reskin detection, and Euler color/texture/structure lenses. State machine needs only Python 3 stdlib; lenses need numpy+Pillow.
dsh-wechat-ro (plugin)
keerzzz/dsh-wechat-ro
Imports a local copy of your own WeChat history on Linux and exposes it to a DSH session: contact, date and keyword search with original-text citations and Beijing time, a sidebar with daily message and text counts, a 7-day trend, per-conversation highlights and to-dos you confirm as your own, plus six read-only history sources. Linux WeChat 4.1.13.26 only; Windows and macOS collection is not implemented.
dsh-recall-rebuild
linkpain/dsh-recall-rebuild
Enhances DSH memory plugins by reconstructing retrieved memory fragments into contextual, emotionally-toned recollections with an LLM before injection, instead of quoting raw text; read-only to the underlying memory store, with multi-source support, per-user IM isolation, sleep consolidation and a JSONL audit log.
web-forager
jiamingshi-jsphys/web-forager
Reads public pages as clean Markdown, keeping text, tables and code blocks while stripping navigation, ads and footers. Search, HTML, PDF, Office documents, RSS and sitemap go through one set of commands, and long documents can be split into chunks that a model can take directly. The same code runs as an MCP server, so an agent can fetch its own sources during a conversation.
dsh-novel-fade
drizzlegig/dsh-novel-fade
Writing a novel of hundreds of thousands, even millions, of words with AI — but always worried it will forget earlier plot, characters and foreshadowing? Loading piles of old chapters into the context every time is not only costly; it also crowds out the room that should go to actual creation. Fade gives the AI a long-form memory that gradually fades: the recent plot stays sharp, the distant story keeps its key points, and important characters and events can be recalled whenever needed. When a chapter is finished, its memory is organized and its text archived automatically — no need to carry the whole novel around. Cut unnecessary token consumption, keep more context and budget for the chapters ahead, and let AI help you write a longer story.