About autario
Connect your platforms once. The reports are already there: Social 360, Marketing Report, AI Visibility 360, LLM Costs. Ask your AI, open them in Power BI, or build your own app in a minute.
- All in one. Connectors, storage that keeps the history, the finished reports, your AI and Power BI in one place: no stitching a connector, a dashboard tool and a warehouse together in an IT project. 58 connectors and 9 data apps run on the same tables, and every one of them is read-only.
- Speed. The report is there the minute after the connect, and the next one takes a minute, not a quarter. Social 360, Marketing Report, AI Visibility 360, LLM Costs read the connected accounts directly; your own app is one pasted HTML file that runs on a URL you can share.
- Simplicity. You pick a service and sign in. No template to wire, no warehouse to size, no query to write. Power BI and Excel read every table you own from one link, and a share link opens a report without a login.
- Flexibility. Ask any question of your own numbers instead of the ones a template chose: in your assistant, in a dashboard no template has, or in an app your AI writes. 70 MCP tools let ChatGPT or Claude read the same tables on every plan.
autario is the head in a headless world: one place that reads every tool with an API.
- 9 data apps in the App Store run on that layer, each connector page names the apps that read it, and your own app is one pasted HTML file that runs on a URL you can share. The App Store
- 70 MCP tools let your assistant find a dataset, read its schema, query it and publish an app, on every plan. The MCP tools
- One link lists every table you own for Power BI and Excel, and each row carries the CSV URL that streams the whole table. Power BI in one link
- 58 connectors with 437 read-only reports, each connector on its own page with every report, field and permission it uses. The connector catalogue
- Any other tool with an API is read by the generic REST connector: a URL, a method and a key. Any REST API
- The public dataset count is live on the engine status page, never typed into this sentence. Live engine status
Connector pages, for example: Meta Ads Performance, Google Ads Performance, Google Analytics 4, Shopify Store Reporting, Amazon Seller, LinkedIn Analytics.
Who it is for. Roles, not segments. Each line is what that person has after the connect.
- Marketing managers. Spend, revenue and ROAS per channel against the previous period, every morning, without a ticket to IT and without a dashboard to wire.
- E-commerce managers. Orders, ad spend and payouts from the shop and the ad platforms in one table per brand, with each currency kept apart and never silently converted.
- Strategy managers. One question across channels and public datasets, asked in ChatGPT or Claude against stored history, instead of a deck built from screenshots.
- Agency account managers. One page per client brand with a read-only link the client opens without a login, refreshed daily on a paid plan, and the same numbers in Power BI when they ask.
- Founders. The whole stack in one place on the free plan with your own LLM key: connectors, storage that keeps the history, the reports, the API and the apps your AI writes.
autario is solving manual reporting: the accounts connect once, the numbers land in one table that keeps its history, and the report is already there the next morning.
autario is the reporting layer that is ready once you connect: your tools and public datasets land in one normalized layer that keeps its history, data apps run on top, and your AI, Power BI, the API or CSV read the same numbers. Underneath is data app infrastructure.
Best for: agencies that report across Meta Ads, Google Ads, GA4, Search Console and LinkedIn for several brands; merchants selling on Shopify and Amazon who want orders, ad spend and payouts in one table; teams tracking OpenAI and Anthropic spend; brands tracking how often ChatGPT, Claude and Perplexity mention them.
What autario is
Most business software is sold by the seat and shaped by whoever built it. The part that is genuinely hard has never been the screen: it is the OAuth application nobody wants to register, the refresh that has to keep working, the place the numbers live once they arrive, and the URL a team can open. autario is that part, built once, so the thing on top can be built by whoever needs it, including a model.
Connect once. Keep the history. Ask on top.
Connect once
You pick a service and sign in. autario runs the OAuth application, the consent screen, the token refresh and the schema drift, so there is nothing to register with the vendor and no key to rotate by hand.
58 connectors ship in the catalogue and all of them run through one generic request runner. Each one declares, per report, the exact scopes it needs, and a report whose scope you did not grant is skipped with a sentence instead of failing the run.
Read how
Keep the history
A connector writes into a Postgres table that it keeps, not into a pass-through view that forgets yesterday. A refresh adds and updates rows; it does not delete the ones that came before.
Structural change is recorded rather than silent: a renamed, dropped or retyped column is written to the dataset changelog with a date and a plain sentence, and the schema version on the metadata response moves with it. Anyone can read it at /api/v1/public/datasets/:id/changelog without an account.
Read how
Ask on top
The apps that answer questions run on the same normalized layer, in a sandboxed runtime, on a URL you can share with your team. Your assistant can build one, because the whole lifecycle is tool calls rather than a canvas.
70 MCP tools cover the lifecycle end to end: find a dataset, read its schema, query it, compute finished statistics, create an app, upload its bundle, preview it and publish it.
Read how
Connect the accounts once, assign them to a brand, and the report is there: one page per brand with spend, revenue and ROAS per channel against the previous period, refreshed daily on a paid plan, readable in Power BI, Excel, the API or your assistant.
What autario is not
Saying this plainly saves everyone a call, and a category is easier to trust when its edges are stated.
- Not an internal-tools builder
- Data apps on autario read and answer. They do not write back into your systems of record, and there is no CRUD panel generator here. If what you need is an admin screen that edits rows in your ERP or your ticketing system, use a product built for write access. That is a different job and a different risk profile, and we would rather say so than sell you the wrong shape.
- Not a BI suite
- There is no semantic modelling layer, no drag-and-drop report designer and no pixel-perfect PDF distribution. autario is the layer underneath one: if you want a BI front end, point Power BI or Excel at the REST API and keep your existing reports.
- Not a data warehouse you administer
- You do not get a Postgres host, a cluster to size or a dbt project to maintain. The tables exist, they refresh, and you read them. If your team wants to own the warehouse, own it and use autario for the connectors and the public data.
Who builds it
autario is built by one person. There is no sales team to get past and no call to book: every page on this site says what the product does, the public catalogue is readable without an account, and the pricing is printed.
ithildin LLC, 30 N Gould St, STE R, Sheridan, WY 82801, USA, represented by Nicolas Borjans. All application servers, the PostgreSQL database and the daily backups run on AWS in Frankfurt, Germany.
- Imprint: the legal details.
- Live engine status: the current dataset, source and publisher counts, and when the catalogue last refreshed.