Archestack

io.github.archestack由 GitHub 帳號 archestack 發布v0.3.0更新於 Nov 6, 2026

Search, rank and compare open-source AI projects with Archestack's open data

已驗證Streamable HTTP可網頁執行知識與記憶開發者工具AI 與機器學習

概覽

AI 產生的概覽

唯讀存取 Archestack 的開源 AI 專案排行榜:搜尋、比較、查看部署需求,並尋找付費工具的替代方案。

可以做什麼
  • 依關鍵字、分類、授權、免 GPU、arm64 或線上示範等條件搜尋並排序兩份清單中的專案
  • 查看單一專案的完整資訊:評分組成、分類名次、GitHub 資料、健康度、連結與評論
  • 取得專案的部署資訊:Docker、arm64、GPU、記憶體、外部服務、連接埠與維護狀況
  • 將 2 至 4 個專案並排比較,並列出某個分類的排名
  • 安裝前檢查 GitHub 儲存庫:是否被收錄、授權、維護狀況、通過或未通過的安全檢查、排名更高的專案
  • 尋找可取代付費或閉源產品的開源專案
適用情境
適合在挑選、比較或審查自架 AI 應用、程式開發代理、MCP 伺服器、技能與外掛時使用,也適合尋找 Cursor、ChatGPT 等付費工具的開源替代方案。
執行需求
可使用 mcp.archestack.com 的託管端點(streamable HTTP),或在本機以 Node.js 22 或更新版本執行 npm 套件。不需要金鑰或帳號。託管伺服器限制每個位址每分鐘 120 次請求。
安裝前請注意
七個工具皆為唯讀,伺服器聲明不記錄提問、無遙測。託管伺服器在忙碌時段可能用完請求額度,大量使用建議改用本機套件。安全檢查結果僅代表讀取當日的實際情況,並非保證;託管伺服器會略過 npm 套件所做的結構描述驗證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Archestack,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.archestack%2Fmcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "archestack": {
      "type": "http",
      "url": "https://mcp.archestack.com/mcp"
    }
  }
}

README

Archestack MCP server

[npm] [license: MIT]

Ask your assistant about open-source AI projects and get answers from the Archestack rankings: scores, GitHub facts, reviews and open-source picks for paid tools.

It covers two lists:

  • Best of AI: self-hosted AI apps and infrastructure, like chat UIs, model servers, RAG, agents and vector databases.
  • Best of Vibe Coding: starters, coding agents, MCP servers, skills and plugins for building with AI.

It reads the open data API. No key, no account. Run it on your machine with npm, or add the hosted server by its URL.

Hosted server

https://mcp.archestack.com/mcp: the same tools over streamable HTTP, for apps that take a URL instead of a command. Read-only, no sign-in.

  • Claude (claude.ai and the desktop app): Settings → Connectors → Add custom connector, paste the URL.
  • Claude Code: claude mcp add --transport http archestack https://mcp.archestack.com/mcp
  • Any client: { "type": "http", "url": "https://mcp.archestack.com/mcp" }

It runs on Cloudflare's free Workers plan, so it allows 120 requests a minute per address and can run out of requests late in a busy day (UTC). It keeps no logs of your questions: privacy. For heavy use, run the npm package below.

Safety allowlist for admins

The hosted server also serves Archestack's safety checks as allowlists: MCP servers whose latest run passed every applicable check, pinned to the package version that was read, each with the official MCP Registry's record of that version.

  • GitHub Copilot ("Registry only" policy): MCP Registry URL https://mcp.archestack.com/registry (v0.1 API: /v0.1/servers, /v0.1/servers/{name}/versions/{version}).
  • Claude Code: managed-mcp.json for a fixed set, or allowedMcpServers for managed settings.
  • The data: /api/v1/allowlist.json. A check result is a fact about what was read on that date, not a guarantee.

Install

Needs Node.js 22 or newer. One click for Cursor or VS Code:

[Add to Cursor] [Add to VS Code]

Claude Code

bash
claude mcp add archestack -- npx -y @archestack/mcp

Claude Desktop: add this to claude_desktop_config.json (Settings → Developer → Edit Config), then restart the app.

json
{  "mcpServers": {    "archestack": { "command": "npx", "args": ["-y", "@archestack/mcp"] }  }}

Cursor: the same mcpServers block in ~/.cursor/mcp.json, or in .cursor/mcp.json for one project.

VS Code without the button:

bash
code --add-mcp '{"name":"archestack","command":"npx","args":["-y","@archestack/mcp"]}'

From source

bash
git clone https://github.com/archestack/mcp.git archestack-mcpcd archestack-mcpnpm ci && npm run build

Then point your client at node /full/path/to/archestack-mcp/dist/index.js instead of npx -y @archestack/mcp.

Tools

ToolWhat it does
search_projectsFinds projects by words and filters: list, category, license family, runs without a GPU, arm64 build, live demo
get_projectOne project in full: score and its parts, place in its category, GitHub facts, health, links, review
deploy_factsWhat it takes to run one project: Docker, arm64, GPU, RAM, outside services, port, its stated needs, upkeep
top_in_categoryThe ranking of one category, best first
compare2 to 4 projects side by side
check_repoBefore you install a GitHub repo: listed or not, license, upkeep, safety checks passed and failed, higher picks
alternatives_toOpen-source picks for a paid product, such as Cursor or ChatGPT

All seven are read-only. Things to ask:

  • "Which vector database runs without a GPU?"
  • "Open-source alternatives to Cursor"
  • "Compare Open WebUI and LibreChat"
  • "Top 5 coding agents with an arm64 build"
  • "Check github.com/ruvnet/ruflo before I install it"

What comes back, shortened (search_projects with "vector database" and no_gpu, data of 2026-10-13):

json
{  "updated": "2026-10-13",  "total": 15,  "results": [    {      "name": "Milvus",      "place": 1,      "score": 81,      "stars": 46366,      "license": "Apache-2.0",      "gpu": "optional",      "arm64": true,      "tagline": "Distributed vector database with dense, sparse and hybrid search at scale",      "source_url": "https://archestack.com/best-of-ai/projects/milvus/",      "checked_at": "2026-10-13"    },    { "name": "Meilisearch", "place": 2, "score": 75, "gpu": "none", "...": "..." }  ]}

How it works

  • It talks to archestack.com and nothing else. The API is static JSON served with the site. The server sends nothing about you or your questions and has no telemetry.
  • The npm server checks each file against the JSON Schema published next to it (/api/v1/schema/). If a file does not match, you get an error instead of a made-up answer. The hosted server skips this check to stay inside the free plan's CPU time; the tests run both against the same recorded files.
  • Each request times out after 8 seconds, with two retries and backoff. The server keeps each file in memory for an hour; Archestack refreshes the data twice a day.
  • Every project in an answer carries source_url, its page on archestack.com, and checked_at, the date its facts were checked on GitHub.
  • ARCHESTACK_API_URL points the server at another copy of the API. The tests use it for a local one.

Data and license

The code is MIT. The data is CC BY 4.0 by Archestack: if you publish something built on it, link the project page (source_url).

Archestack checks every project on GitHub: stars, last commit, license, Docker files. How the score works: archestack.com/methodology/.

Development

bash
npm cinpm test           # builds, then runs the server over stdio against recorded API answersnpm run fixtures   # records fresh answers from archestack.com into test/fixturesnpx @modelcontextprotocol/inspector node dist/index.js   # try the tools by handnpx [email protected] dev   # the hosted server on http://localhost:8787/mcp

src/worker.ts is the Cloudflare Worker entry (config in wrangler.jsonc); npm run deploy publishes it with CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID set.

Bugs and ideas: open an issue.

來源:README.md,提交 f6317ad

工具

7

search_projects

Search projects

Find open-source AI projects across both Archestack lists by words and filters. Words match names, repos, taglines, categories and the products a project replaces; results rank by how many words match, then exact names, then projects whose name or category holds the words, then by score. Put hard needs in the filters, not the words (no_gpu instead of "without a GPU").

輸入參數listarm64limitqueryno_gpulicensecategoryhas_demo

get_project

Get a project

Everything Archestack has on one project: score and the parts it is made of, place in its category, GitHub facts (stars, license, last commit and release, language, Docker, arm64, GPU, RAM, external services, port), project health, demo and docs links, and the review (summary, audience, strengths, weaknesses).

輸入參數project必填

deploy_facts

What it takes to run a project

The facts an agent needs before installing or deploying one project: Docker files, arm64 build, GPU need, minimum RAM, outside services it needs, web port, what its README says it needs, docs and demo links, and upkeep (latest release, releases in 12 months, security advisories, its package). null means Archestack does not know. Archestack does not track hosting cost or deploy templates.

輸入參數project必填

top_in_category

Top projects in a category

The ranking of one category, best first, with score and tagline. An unknown category returns the list of categories.

輸入參數listlimitcategory必填

compare

Compare projects

Put 2 to 4 projects side by side: score and its parts, place, stars, license, last commit, Docker, arm64, GPU, RAM, external services, strengths and weaknesses.

輸入參數projects必填

check_repo

Check a repo before installing it

Check a GitHub repo before installing it, most useful for an MCP server, skill or plugin: whether Archestack lists it, its license in plain words, upkeep, the safety checks it passed (with the failed ones and their evidence) and up to 3 higher-ranked projects in its category. "Checks passed" means those checks passed, not that the code is safe. A repo Archestack does not list returns listed: false and a link to suggest it.

輸入參數repo必填

alternatives_to

Open-source alternatives

Open-source projects that replace a paid or closed product (e.g. Cursor, ChatGPT, Notion), highest score first. own_claim is true when the project says so in its own README.

輸入參數product必填

版本歷史

4
  1. v0.3.0最新Oct 23, 2026
  2. v0.2.0Oct 15, 2026
  3. v0.1.5Oct 14, 2026
  4. v0.1.4Oct 13, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分