dsh-llm-ai
★ 0dsh-llm-aimodels.dev-cataloged multi-provider LLM adapter for the DeepSeek Harness LLM seam
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WooLeo1995/dsh-llm-aiDiscover The Best DSH plugins
DeepSeek Harness plugins — Page 775
25187results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-llm-antigravityAntigravity route for DeepSeek Harness: local Antigravity CLI (agy) as an LLM provider
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangzhangco/dsh-llm-antigravitydsh-llm-api-pool为 opencode go 设计的 API 池:根据余额热管理切换不同 API key,官方用量/余额查询 + 设置页图形化管理。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bainianlaoyao/dsh-llm-api-pooldsh-llm-assistantResident DeepSeek assistant seat for DeepSeek Harness: chat, reminders, and on-demand read-only task reference
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NOirBRight/dsh-llm-assistantdsh-llm-auto
★ 0dsh-llm-autoDSH 宿主插件:注册一个 `auto` 模型路由,内部按配置的有序链依次尝试多条「provider + model」;某条在**产出任何内容之前**失败时,先按官方同款策略在该路由内原地重试(瞬时错误白名单,默认 5 次),重试耗尽才静默切下一条,对上层表现为一个普通模型;并可用 compactWindow 把自动压缩点钉在指定 token 数附近。0.4.0 起自带浏览器半侧:插件页该 bundle 的卡片上直接渲染配置表单,可直接改 compactWindow(官方 SettingsForm 原语,保存才写入)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liuyun847/dsh-llm-autodsh-llm-auto-routeProvider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qinyu765/dsh-llm-auto-routedsh-llm-bailian-kimi百炼（DashScope）上的 Kimi LLM 适配器插件：支持 kimi-k3 图片输入、思考链与工具调用
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sologuy/dsh-llm-bailian-kimidsh-llm-balanceDeepSeek Harness plugin for querying LLM service provider usage: reads each configured provider's remaining balance or subscription quota and shows it in an always-visible card in the web GUI.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlienGene/dsh-llm-balance-siderbardsh-llm-balanceShow LLM API balances under the chat input: DeepSeek, OpenRouter, SiliconFlow and any custom provider with a balance endpoint.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JonyChan8394/dsh-llm-balancedsh-llm-bounded-retryBounded all-error request retry plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:911218sky/dsh-llm-bounded-retrydsh-llm-call-inspectorSession-scoped LLM request and response inspector for DeepSeek Harness Web
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:striveh/dsh-llm-call-inspectordsh-llm-captureInspect raw LLM requests and responses in DeepSeek Harness Web
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chengzhicao/llm-capturedsh-llm-chatgpt-oauthChatGPT Plus/Pro OAuth model provider for DeepSeek Harness, backed by pi-ai's openai-codex route.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangxiubo/dsh-llm-chatgpt-oauthdsh-llm-chatgpt-webChatGPT Web (owned Chromium driving Temporary Chat) adapter for the DeepSeek Harness LLM seam
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:twilightt1/dsh-llm-chatgpt-webdsh-llm-codebuddy-powerA full-featured CodeBuddy (WorkBuddy) provider plugin.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pgnqukezrdxmhjso/dsh-llm-codebuddy-powerdsh-llm-codexCodex route for DeepSeek Harness: local Codex CLI first, OpenAI-compatible API fallback
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangzhangco/dsh-llm-codexdsh-llm-commandcodeDeepSeek Harness (dsh) LLM adapter for Command Code, routing models through the generate endpoint a Go plan can reach — including image input.
dsh-llm-configMulti-provider LLM configuration for the DeepSeek Harness LLM seam: declare any number of providers, each with its own endpoint, credential and per-model parameters, across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EmotionG/dsh-llm-configdsh-llm-configMulti-provider LLM configuration for the DeepSeek Harness LLM seam: declare any number of providers, each with its own endpoint, credential and per-model parameters, across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EmotionG/model-importdsh-llm-cost
★ 0dsh-llm-costPer-turn and whole-session LLM cost meter for DeepSeek Harness (DeepSeek / GLM official prices, peak and off-peak tariffs, Chinese statutory holidays).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liandy0731/dsh-llm-costdsh-llm-databricksCommunity Databricks AI Gateway LLM plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhuchengde0214-ctrl/dsh-llm-databricksdsh-llm-error-classifyDSH 错误分类修正插件：把 pi-ai 适配器一律判成 AUTH 的提供方失败改写为 PROVIDER_ERROR，让网关原文原样显示，而不是被 UI 替换成「API 密钥无效」。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lxl8182/dsh-llm-error-classifydsh-llm-error-retryDSH (DeepSeek Harness) 插件：大模型请求报错时按规则休眠后自动重试。支持 HTTP 状态码 / 机器码 / provider 返回字段=值 三种命中形态，每条规则独立配置休眠时长与最大重试次数；会话框内显示重试卡片，GUI 设置页实时编辑规则。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liaoyuqing/dsh-llm-error-retrydsh-llm-eval
★ 0dsh-llm-evalLLM 评估：输出质量评估、幻觉检测、基准测试、回归守护。受 wshobson/agents（38k★ MIT）启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-llm-evalFind the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.