DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
73 个项目，匹配「open」
kuaiyukuaikuai
DSH plugin: scan other AI agents (Codex, Claude Code, cc-switch, Hermes, opencode, Gemini, Grok, Kimi, CodeBuddy, Trae, OpenClaw, Qoder, WorkBuddy, Cursor, ...) and one-click sync their MCP servers and skills into DSH.
taikaikaikai-pixel
Unofficial DeepSeek Harness (dsh) plugin: turn CodeBuddy, TraeWork CN & Qoder CN subscriptions into 20+ chat models — OAuth, multi-key rotation, web search/fetch, image generation, OpenAI-compatible registry.
wenzetan
NewAPI (OpenAI-compatible gateway) LLM provider plugin for DeepSeek Harness (dsh): chat-only model discovery + Web settings section. Zero dsh modifications.
BigBlueBaby
把 Codex（OpenAI Codex CLI / Desktop）的 MCP 服务器、技能、全局指令、记忆与会话历史一键迁移进 DeepSeek Harness（DSH）——可视化面板 + CLI，源码只读、dry-run 预览、密钥按原样迁移。
EDMOK
MCP server empowering text-only LLMs with image analysis via any OpenAI-compatible vision API
JuneLearn
让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call
Luck9Star
Generic LLM gateway provider plugin for DeepSeek Harness: newapi / LiteLLM / Higress / any OpenAI-compatible gateway, multi-protocol (OpenAI/Anthropic/Gemini) via pi-ai SDK, models.dev enrichment
Sur-Cai
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.
dhicoc
dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).
dqsjqian
Industrial-grade C++23 Agent Tooling Framework GUI — provider-agnostic LLM agent with true SSE streaming (Continuo transport), tool registry, approval gate. Built on Aria (C++23 MVVM).
SHOPLINE AI Toolkit for DeepSeek Harness (dsh-plugin): official SHOPLINE Developer MCP bridge + SHOPLINE agent skills, mirroring the Shopify AI Toolkit architecture. dsh-plugin
Leeminjing
[RETIRED] dsh >= 0.2.0 fixes orphaned tool_calls in the runtime (ToolCallRecovery in dsh-agent-loop). Do not install.
keman-ai
Bring OpenCode Zen's free models to DeepSeek Harness — zero config, no API key, catalog discovered live from upstream
supersealwqas
DeepSeek Harness 第三方 API 与自定义模型设置插件：支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
tearslee
DeepSeek Harness (dsh) plugin: supervise a workbuddy2api gateway process and auto-register its models as an LLM provider
Jesse-njx
dsh-polyglot — the model switch for DSH: generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek presets, automatic provider fallback on rate limits
OpenSaozi
接入 Google Anti Gravity Coding Plan 作为 DeepSeek Harness LLM Provider，直接使用账号下的 Gemini / Claude / GPT-OSS。 | Google Anti Gravity Coding Plan LLM Provider for DeepSeek Harness.
agent-plaza
Zero-signup public commons for AI agents — HTTP API + Agent Skill (Codex, Cursor, Hermes)
aybrt
WorkBuddy (CodeBuddy Code ???) ???? DeepSeek Harness:?? OpenAI ???? + pi-ai provider ?? + ?????
b8yg7vjstj-ctrl
DeepSeek Harness plugin: local llama.cpp (llama-server) as a first-class model provider — process/router management, catalog sync with mmproj vision pairing, auto-start, stop-then-load switching, and a sidebar terminal monitor panel.
baaai123
该仓库暂未提供项目说明。
huyang2024
OpenAI-compatible HTTP surface for DeepSeek Harness (dsh): POST /v1/chat/completions, POST /v1/responses, GET /v1/models over the harness webServer + llm runtime
kam74515-boop
Import local Codex / Grok / Claude / OpenCode / CC Switch logins into DeepSeek Harness
linxuhao
DeepSeek Harness plugin for local image / voice / music / SFX generation: the same character stays the same character across calls, degenerate output is refused rather than returned, and the GPU is untouched when idle. Hand the image half to any OpenAI-shaped API instead and its engine and 10.1 GiB of weights are never installed.
