DeepSeek Harness Remote
DeepSeek Harness Remote 可将手机或另一台电脑与你运行 DeepSeek Harness 的电脑安全连接,随时随地继续你的工作,方便随时查看进度并继续工作。
翻譯準備中
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證製作者的介紹僅有上面的一句話。 更多詳情請閱讀儲存庫 README。 儲存庫 README ↗
正在載入完整 README。
檢視完整 README ↗This is a Next.js project bootstrapped with create-next-app.
Create a .env.local (or local.env) and set your Supabase keys and OpenAI key.
Required variables:
OPENAI_API_KEY — OpenAI API key used for intent classification and planning.POSTHOG_API_KEY — PostHog project API key used for server-side analytics and LLM observability.POSTHOG_HOST — PostHog ingestion host, defaults to https://us.i.posthog.com.NEXT_PUBLIC_SUPABASE_URL — Supabase project URL.NEXT_PUBLIC_SUPABASE_ANON_KEY — Supabase anon key for SSR clients.SUPABASE_SERVICE_ROLE_KEY — Service role key for server-side inserts/storage.Agent SDK Feature Flags (safe rollout):
AGENT_SDK_ENABLED — when true, the /api/agent/run endpoint returns AgentResult directly.AGENT_SDK_SHADOW — when true and AGENT_SDK_ENABLED is false, the route returns legacy response and runs the agent in the background (metrics logged).AGENT_SDK_MODEL — model to use for classification/planning (default gpt-4o-mini).Defaults are provided in .env.example.
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
Open http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
To learn more about Next.js, take a look at the following resources:
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
npm run dev — Start local dev server with hot reload.npm run build — Production build (Next.js + TypeScript).npm start — Run the compiled production server.npm run lint — Lint code with ESLint.npm run test:contracts — Run contract tests for legacy and agent schemas.npm run bench:agent — Run enhancement benchmark (see scripts/bench-agent.mjs).The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.