Generated Computers
Locals: an Apple Silicon engine that runs local LLMs up to 3x faster. A product of Generated Computers.
翻譯準備中
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
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Where humans and agents find each other, signal what they need, and show what they can do.
翻譯準備中
取自儲存庫 README
正在載入完整 README。
檢視完整 README ↗The curated directory for the agentic web — AI agents, MCP servers, and agentic tools with real API, MCP, CLI, or browser-extension access. Live at agentswitchboard.dev.
A listing marked Verified is one we checked works: its URLs load and its declared access (API, MCP, CLI or extension) responds. Re-checked monthly; the label drops if it stops working.
Point any MCP client at it and query the catalog with native tools:
{
"mcpServers": {
"agentswitchboard": { "url": "https://agentswitchboard.dev/api/mcp" }
}
}
Tools: search_agents · get_agent · list_categories · compare_agents ·
alternatives_to · connect_bundle (one MCP client config for up to 10
listings) · submit_listing (files a public GitHub issue for review; publishes
nothing). Streamable HTTP, no auth. Stdio-only clients:
npx -y mcp-remote https://agentswitchboard.dev/api/mcp
Setup for Grok, Grok Bot, the xAI API, Claude, and ChatGPT: agentswitchboard.dev/connect.
Prefer plain HTTP? There's a REST search too:
curl "https://agentswitchboard.dev/api/agents?q=video&access=mcp&limit=5"
curl "https://agentswitchboard.dev/api/agents/agentmail"
curl "https://agentswitchboard.dev/api/categories"
curl "https://agentswitchboard.dev/api/compare?a=deepgram&b=assemblyai"
curl "https://agentswitchboard.dev/api/bundle?items=linear,sentry-mcp,playwright-mcp"
OpenAPI: /openapi.json.
Connector skill: /skill.md.
Also machine-readable: /agents.json
(full catalog, CORS-open), in-browser tools via WebMCP (document.modelContext),
and an agent-optimized view on every page (the "For Agents" toggle).
Full API reference: docs/API.md — REST search/detail/categories, compare, alternatives and the connect bundle, MCP, WebMCP, and the catalog dump.
The entire catalog lives in this repo:
content/
agents/<slug>.json one file per agent — the source of truth
categories.json category definitions
changelog.json public audit log (rendered at /changelog)
There is no database and no CMS. Editing content = editing files. Merging to
main = publishing. Every entry is schema-validated in CI
(scripts/validate-content.ts) — a bad entry
cannot merge. A weekly job link-checks every listing's agent and provider URLs.
Want to add or fix a listing? See CONTRIBUTING.md. Non-developers: agentswitchboard.dev/submit.
npm install
npm run dev # no env vars needed — content is right here
| Command | |
|---|---|
npm run dev | dev server |
npm run build | production build (SSG, all pages) |
npm test | unit tests |
npm run lint / npm run typecheck | quality gates |
npx tsx scripts/validate-content.ts | validate the catalog |
npx tsx scripts/check-links.ts | link-rot sweep |
npx tsx scripts/cms.ts | content ops: find / feature / update / unpublish |
npx tsx scripts/weekly-drop.ts | batch-add agents (see file header) |
npx tsx scripts/drop-impact.ts | what a content change does elsewhere on the site, compared with origin/main |
Stack: Next.js (App Router) · Tailwind · file-based catalog · deployed on Vercel.
app/, components/, lib/, scripts/, config) — MITcontent/, including every content/agents/*.json listing, and the same data at /agents.json, the REST API and the MCP server) — CC BY-NC 4.0: reuse for non-commercial purposes with attribution to Agent Switchboard; contact us for commercial use. Submitted listings are contributed under CC BY-NC 4.0. (Versions up to 2026-09-25 remain CC BY 4.0.)