
Atlas
io.github.AtlasDevHQ由 GitHub 帳號 AtlasDevHQ 發布v0.0.2更新於 Oct 24, 2026
Atlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.
發布方自己的服務:Red Atlas Api
概覽
Atlas 是以 YAML 定義的語意層分析工具,讓 AI 助理根據有來源、經人工確認的公司資料回答問題。
- 可以做什麼
- 透過語意層回答公司資料問題,答案標示為實測、已確認或原始紀錄,並附上來源與日期。對已設定的資料來源(如 Postgres、MySQL、ClickHouse、Snowflake、DuckDB、BigQuery、Salesforce)執行唯讀、單一語句、資料表白名單驗證的 SQL。未設定資料來源時使用內建的 NovaMart 示範資料集。遇到矛盾時同時呈現雙方說法與來源,涵蓋不足時明確說明而不猜測。可連接本機或自架的 Atlas API,沿用其資料連線、語意層與治理規則。
- 適用情境
- 適合希望助理根據自有公司資料回答分析問題、並保留可追溯來源與人工確認事實的情境,而非自由生成 SQL。也適合在自有 VPC 中自架 Atlas,並從 Claude Desktop、Cursor、Continue 等用戶端查詢的團隊。
- 執行需求
- 透過 npx(或 bunx)以 stdio 本機程序執行。需要執行中的 Atlas API,以 ATLAS_API_URL 指定(預設指向本機位址),或在 ATLAS_DATASOURCE_URL 提供資料來源位址;兩者皆無時改用內建 NovaMart SQLite 示範資料。ATLAS_PROVIDER 為選用項目,僅在同時執行 Atlas 聊天元件時需要。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Atlas,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Atlas
Atlas is the company facts your AI agents can trust: every one carries its source, its date, and the name of the person who approved it. Open source, runs in your VPC.
The hosted service is shut down. I ran Atlas as a hosted service at useatlas.dev until September 2026 and have now turned it off, along with the hosted demo and docs.useatlas.dev. Atlas continues as open source: everything below runs on your own machine or in your own VPC. The docs live in
apps/docs/content.
Point Claude Desktop, Cursor or Continue at a local Atlas with one command. With no datasource configured it uses the bundled NovaMart demo data:
Restart the client and ask it a question about NovaMart's orders. (Claude Code, VS Code and other clients: the same command with --client generic prints a block to paste. On WSL2, write bun x instead of bunx.)
How it works
Three kinds of thing live in the Atlas, and every answer says which it is drawing on:
- Surveyed — read straight from your company's own data through a semantic layer you author. True by construction: the query re-reads live rows, nobody interpreted anything, and it cannot go stale between readings. SELECT-only, single statement, table-whitelisted, validated seven ways before it runs.
- Attested — extracted from something someone wrote, then approved by a named person in your company. That person is on the record, and the fact carries its source and its date.
- On the record — the raw source material itself, unedited. Trustworthy as testimony, not as fact.
Surveyed outranks Attested wherever they overlap, so a recollection never overwrites the data. Nothing becomes Attested without a person approving it, and there is no setting that turns that off. Contradictions are shown with both claims and both sources; Atlas does not pick a winner. Where nobody has surveyed, the coverage page says so instead of guessing.
Run it
- Self-hosted — the complete Atlas under AGPL, in your VPC, free; Docker, Railway or Vercel. Self-host quick start.
- From your AI agent —
bunx @useatlas/mcp init --localagainst a local Atlas, orbunx @useatlas/mcp init --hosted --api-url <your Atlas>against a self-hosted one with managed auth. MCP guide.
Where everything else went
This README used to inventory the whole product. Each section now lives on one docs page, in the docs source:
- The four context surfaces (semantic layer, Knowledge Base, learned patterns, the Company Atlas) and where answers show up — Introduction
- The YAML semantic layer and a worked
orders.yml— Semantic layer - The NovaMart dataset and the canonical questions — Demo datasets
- The local scaffold (
bun create atlas-agent) — Self-host quick start - The embeddable widget and React component — Embedding widget
- How Atlas compares to Genie, Cortex Analyst, Hyper, Glean and the text-to-SQL peers — Comparisons
- Deploy buttons, starters and Docker Compose — Deploy
- The SQL validation pipeline and sandbox threat model — SQL validation, Sandbox architecture
- Environment variables — Reference and
.env.example - Plugins, datasources, chat platforms and connectors — Plugin authoring, Integrations
- Supported databases and LLM providers — Connect your data, Model routing
- The Knowledge Base, dashboards, and bringing your own frontend — Knowledge Base, Dashboards, Frameworks
- The CLI (
atlas init,atlas diff, and the rest) — CLI reference - The monorepo layout and dev setup — CONTRIBUTING.md
- What is open source and what is commercial — Enterprise boundary
Acknowledgments
Atlas was inspired by Abhi Sivasailam's work on Vercel's internal data agent d0 and the open-source vercel-labs/oss-data-analyst template. The core insight — invest in a rich semantic layer, trust the model, and keep the tool surface minimal — came from that work.
License
The server and core packages are AGPL-3.0: if you modify the server and serve it to users, you share those modifications. The client libraries (@useatlas/sdk, @useatlas/react, @useatlas/types, @useatlas/plugin-sdk, @useatlas/mcp) and all plugins are MIT. The ee/ directory is source-available under a commercial license; nothing that makes the Atlas work is behind it — only governance, convenience and scale. Full inventory: Enterprise boundary.
來源:README.md,提交 ba3931e
工具
0版本歷史
1- v0.0.2最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
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25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Atlas 整合
Red Atlas Api
red.atlas官方發布者
遠端 MCP 伺服器,讓助理存取波多黎各與哥倫比亞的房地產資料:物件、成交、地號、許可、分析與 AVM 報告。

Election Atlas
由 GitHub 帳號 TaltonFiggins 發布
一個美國與加拿大選舉地理的遠端圖集,讓助理查詢地名、選區、邊界和民意代表。

Boundary Atlas
由 GitHub 帳號 TaltonFiggins 發布
提供美國與加拿大行政邊界的遠端地圖集,讓助理查詢地名、判斷某點所屬選區,並取得 GeoJSON 多邊形。

Atlas Primer Voice Roleplay
由 GitHub 帳號 AtlasPrimer 發布
在 Atlas Primer 上建立即時 AI 語音角色扮演模擬和行為評估。AI 翻譯

Smart Rings Atlas
由 GitHub 帳號 thiazzz 發布
用於智慧戒指研究的遠端 MCP 伺服器:檢索附日期的紀錄、比較證據、估算訂閱成本並尋找地區購買連結。