Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
397 plugin trovati
dsh-lcm
zy-xyz/dsh-lcm
Lossless context compaction: an LLM summarizes a leaf of compacted events and replaces it with one checkpoint node, nothing is deleted, so lcm_search still matches text a checkpoint summarized and lcm_expand restores any event by seq. Summaries condense at fanin 4, a threshold crossing sweeps several leaves under two clocks, and an idle pass resumes a sweep that ran out of budget. Optional semantic recall ranks events against any OpenAI-compatible embedding endpoint, with a /lcm-embed backfill command and status. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-llm-sampling-params
devhang/dsh-llm-sampling-params
Injects per-model sampling parameters into chat-completions requests to OpenAI-compatible gateways: a fetch wrapper looks the request body's model id up in a configured models table and sets temperature, top_p, top_k, min_p, repeat_penalty, presence_penalty and frequency_penalty on requests whose URL carries /v1/chat/completions, plus repetition_penalty for SGLang and vLLM.
dsh-prompt-forge
vhow123/dsh-prompt-forge
Image-generation prompt workshop in the sidebar panel list, working in four directions that share one result. Idea to prompt: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history. Image to prompt: drop a reference image and a vision model reverse-engineers the same fields. Prompt to prompt: type one line such as light turns to dusk and only the named fields are rewritten, everything else is copied verbatim. Prompt to image: the result card, or the panel itself before any optimization has run, renders through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a main image attached it posts to /images/edits and carries up to four extra references, with only text it posts to /images/generations. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The first two directions and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-cliproxyapi-provider
thebtf/dsh-cliproxyapi-provider
Connects one CLIProxyAPI gateway to DeepSeek Harness, speaks OpenAI Responses, Chat Completions, Anthropic Messages or Google Generative AI natively, and imports the gateway model catalog into a settings page where each model can be selected.
dsh-plugins (dsh-connect-agentscope-platform)
summerscar/dsh-plugins
AgentScope Platform inside DeepSeek Harness: manage several platform accounts (switch the billing account by hand, pick one by remaining Credits, probe and flag unhealthy ones), an optional OpenAI-compatible model provider whose catalog you can fetch, add to and edit row by row, an available-Credits and redeemable-contribution readout under the composer, and a settings panel for the daily check-in, the balance, contribution grants, usage detail and the price list. Switching accounts affects new requests only and never interrupts a session already in flight.
dsh-subscription-balance
yanboyang97/dsh-subscription-balance
Shows the balance or quota behind the current conversation's model for DeepSeek, Kimi Code and OpenAI, plus local usage and priced estimates for every provider configured in DSH.
dsh-gpt-adapter
lxjmaster/dsh-gpt-adapter
DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.
dsh-toolcall-id-repair
zyf2492313716-cloud/dsh-toolcall-id-repair
Stops session lockups from OpenAI-compatible gateways that stream empty tool-call ids: intercepts llm/stream chunks in memory to synthesize consistent call_<sha256> ids across tool-call-delta and block-end, plus offline session repair/verify scripts under tools/.
dsh-voice-dialog
qinfpv/dsh-voice-dialog
Continuous voice conversation for DSH: auto sentence splitting, a 2-second confirm window before sending, and spoken replies you can interrupt by speaking. Speech is recognised by DSH's own speech service by default (a local Whisper bridge or an OpenAI-compatible endpoint can be set instead), the recognised text is corrected by a DSH model call, and replies are read aloud through Microsoft Edge's online text-to-speech service, so reply text is sent to Microsoft. A daily check of PyPI and Hugging Face for faster-whisper updates is on by default; settings and any API keys are stored in plain text in ~/.dsh/voice-tutor-config.json. Its /voice-tutor routes require an authenticated DSH session (admission is checked per request), API keys are never returned, and applying an update needs a one-time confirmation token.
dsh-video-gen-plugin
adithyanraj03/dsh-video-gen-plugin
Generates video through the user's own OpenAI-style asynchronous endpoint and plays the finished clip in the conversation, with live progress and cancel.
dsh-qwen-mode
fuxfantx/dsh-qwen-mode
Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.
agentdeck-super
wm17717783258-boop/agentdeck-super
Nexi 灵犀:超级 Agent + 多 Agent 小组协作 + MCP 网关。一个会自己干活的 Agent,能把本机 CLI、ACP、OpenAI 兼容、桌面 App、自研桥接的多类 Agent 编成小组,并用一条命令把同一套能力接进 Claude/Cursor/Codex 等宿主。
dsh-appearance
mei0769/dsh-appearance
Generate a persona appearance image from hair, outfit, accessory and expression text, then save it to a local gallery. Works with any OpenAI-compatible images API and also reports the composed prompt and backend status. Needs an images API key: it defaults to SiliconFlow (Qwen/Qwen-Image) and you set baseUrl, model and apiKey in the plugin config.
dsh-totonai
zemyao7/dsh-totonai
Account-based access to the ToTonAI gateway inside DeepSeek Harness: sign in or register in the settings panel, use 65 mainstream models (GPT, Claude, Gemini, DeepSeek, Doubao, Grok, GLM), and pick a plan then pay by QR code in the same panel. Upstream API keys stay on the server.
dsh-provider-pool
vamyane/dsh-provider-pool
Provider pool for DeepSeek Harness. It runs a local OpenAI-compatible proxy that tries configured LLM providers in priority order and falls back on authentication, quota, rate-limit or server errors, with per-provider usage statistics.
dsh-oneapi
szluyu99/dsh-oneapi
Configuration panel for an existing `oneapi` route of the pi-ai provider adapter (declare that route in the llm-pi-ai settings first, with api: openai-completions): edit display name, Base URL, API key and default model, test connectivity per model and sync the model list from the gateway, with six agent tools and an optional left-sidebar panel. Written for a Baidu-internal gateway: the Base URL placeholder and token link point there, so set your own OneAPI-compatible gateway.
dsh-memelens
whatif146/dsh-memelens
Explains Chinese internet memes to an agent: registers a meme_explain tool that returns the meaning, tone, origin and lifecycle of a sticker, which memes can and cannot be combined, occasions to avoid, and both a meme-version and a plain-version reply. Answers come from a local memory store with spacing-effect decay, falling back to a user-configured OpenAI-compatible vision endpoint (BYOK).
dsh-codex-workbench
vlad1108/dsh-codex-workbench
Adds ChatGPT sign-in, Codex subscription quota (5-hour and weekly windows) and Codex-backed web search to DeepSeek Harness; installing it switches the profile's web search provider to openai-codex.
dsh-connect-modelscope
iffcheckpass/dsh-connect-modelscope
ModelScope connector: OpenAI-compatible chat models, a Models-page provider entry, and a composer magicube balance while a ModelScope model is selected.
dsh-vision
young-felix/dsh-vision
Ask a vision-capable model about a local image from any session, including sessions whose own model is text-only. On the default path the plugin calls the host's route in-process with ctx.llm.stream(), so the host's credentials stay inside its provider adapters; only the optional direct/custom OpenAI-compatible routes read one key (from the plugin config or an apiKeyRef into ~/.dsh/.credentials.yaml).
stickerwu-imagegen
stickerwu/stickerwu-imagegen
Image generation and editing with configurable APIs, reference images, and an on-demand annotation canvas. Requires your own OpenAI-compatible image API endpoint and key.
dsh-stateful-responses
zhexuany/dsh-stateful-responses
Makes DSH's OpenAI Responses calls stateful: after the upstream confirms it stored a response, each turn sends only the newly added input items plus previous_response_id, and a stateless upstream is detected on the first response so every later request falls back to the full history.
dsh-open-bots
dev-bravelo/dsh-open-bots
Adds lasting bots with their own name, photo, persona, memory, voice and model, a Bots panel in the sidebar, and a hidden helper subagent per bot that follows the conversation, searches ahead and leaves notes the bot reads; voice uses your own ElevenLabs, OpenAI, Groq, Mistral or Deepgram key. Interface and prompts in Brazilian Portuguese.
dsh-plugins (dsh-ima)
cc1104666/dsh-plugins
Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.