CATEGORY
Verified manifests and exact versions in this category.
tokan-dsh-token-analytics
DSH plugin for token usage analytics, cost tracking, and optimization signals
dsh-model-jury
Structured cross-model peer review for DeepSeek Harness
dsh-plugin-subs
DSH plugin: OAuth sign-in for Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE — expose subscription LLMs as DeepSeek Harness providers
dsh-deepseek-quota
DeepSeek API quota widget for the dsh web GUI: shows remaining DeepSeek API balance in a floating card pinned to the bottom-right corner (shell.overlay slot).
dsh-claude-bridge
Use a Claude Pro or Max subscription as a DeepSeek Harness model provider, by driving the Claude Code CLI through the Agent SDK.
dsh-modelprint
DeepSeek Harness plugin: fingerprint the provider, model id, sampling, offered tool schemas, and system-prompt prefix of each request, and diff the live card against a pinned one through the modelprint_check tool
dsh-provider-veark
火山方舟 Coding Plan LLM provider for DeepSeek Harness — 图片走 Ark Files API 优先(input_image + file_id),base64 data URL 自动兜底,Responses API 流式
dsh-catalog-refresh
Rebuild DSH's pi-ai model catalogues at runtime: fetches the live model lists from OpenRouter, OpenCode Zen, Fireworks, Groq, Together and DeepSeek and patches the harness's installed pi-ai MODELS registry, so the model picker and discovery show fresh models without hand-adding custom models.
@deepseek-ai/dsh-rss
RSS reading and model tools for DeepSeek Harness
@wuxie233/dsh-agent-teams
AgentTeams for DSH (Wuxie233 fork): per-member model routing, read-only role deny lists
dsh-plus-plus
DSH++ — a Windows-first lifecycle & provider manager for DeepSeek Harness (dsh). Minimal, local-first, zero-runtime-deps.
dsh-llamacpp
DeepSeek Harness LLM adapter plugin for a local llama.cpp server over its OpenAI-compatible /v1/chat/completions API.
@jason666not/dsh-submodel-change
Let the user pick which provider/model drives each subagent when the AI delegates.
dsh-better-model-setting
DSH plugin that replaces the official Models settings page: provider management, per-model reasoning effort, retry overrides, drag reorder, credential status, upstream model sync, and fixed model deletion
dsh-model-picker-search
Adds a search field inside the model picker menu of the composer. Drop-in replacement for the native model seat, sharing the same per-session ModelDirectory so /model popup, the effort selector, and the /model command stay consistent.
dsh-model-capabilities
Edit per-model `input` modalities (text/image) and `reasoningEfforts` from the DSH Settings UI instead of hand-editing settings.yaml. Works on DSH Web and DSH Desktop.
lynkr-dsh-plugin
DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.
dsh-llm-lmstudio
LM Studio (OpenAI-compatible local server) chat-completions adapter plugin for DeepSeek Harness
dsh-model-auto-hot-switch
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.
xby-chucknorris
ChuckNorris MCP server is a tool that provides enhanced prompts to large language models through dynamic schema adaptation, primarily for security research and evaluation.
dsh-super-subscriptions
Supercharged subscription-based LLM provider aggregator for DeepSeek Harness (ChatGPT/Codex, Grok, Google AntiGravity, Claude, Copilot) with unified auth, quota pooling, and zero-config defaults.
dsh-subagent-route-badges
在 DSH 已打开子代理的 Header 展示 provider、model 和 reasoning effort
dsh-ui-balance
Display DeepSeek API account balance under each assistant turn
dsh-commandcode-plan-autosync
Sync CommandCode plan models (goat/pro/max) from the official models API + GOAT plan catalog into llm-pi-ai providers commandcode-<plan>-autosync (one-click create/update in settings).
dsh-conversation-cost
Per-conversation DeepSeek API cost badge for DeepSeek Harness: a zero-dependency session projection pricing each LLM step against the official rate card, with a live cost badge and hover card in the web conversation header.
dsh-smart-model-router
Task- and quota-aware virtual Auto model router for DeepSeek Harness
dsh-deepseek-peak-valley
DeepSeek time-based billing widget (DSH client plugin): automatically determines peak and off-peak periods based on Beijing Time, with 11 sidebar widget styles and a settings page; the dual-view style supports time-based billing and actual usage for the current session (token-meter), with estimated
dsh-free-model
OpenRouter free-models browser plugin (dual-face): fetch OpenRouter models, filter the free ones (price 0 or :free), list them newest-first in a Settings tab with local search and full model info, and create a ready-to-use DSH model config (settings.yaml route + stored credential) in one click. Bili
token-stat
DeepSeek Harness token usage statistics plugin: cumulative usage by model/date, dashboard on the settings page, and online data storage directory changes
dsh-model-select-style
DSH web UI plugin: replaces the official “Model Selection” control in the input box with two independent buttons (provider selection + model selection, linked in two levels), while retaining reasoning level adjustment; only modifies this control and does not change DSH source code.