Built and run by one person.
Tremor: A Free, No-Auth API for 330+ Macro and Market Indicators, 350K records, Refreshed 3x/Day. Ask your AI to explore.

Tremor: A Free, No-Auth API for 330+ Macro and Market Indicators, 350K records, Refreshed 3x/Day. Ask your AI to explore.

Published: July 12, 2026

A free, open API and MCP server for macro, credit, valuation and market data, at tigzig.com's Tremor. Point an AI agent at it and it reads the whole catalog, picks the indicator, and pulls the series itself, no key, no sign up, nothing to configure.

Paste this to your AI coworker (Claude Cowork / ChatGPT Work / Claude Code / Antigravity etc):

"Go to tigzig.com's Tremor API and help me explore the macro data."

The AI connects to the Tremor API, reads the category menu (8 high-level buckets), drills into the one that matches your question, gets the full indicator list with metadata, searches if needed, then pulls the series. One prompt. You never touch the docs yourself. MCP also available if you'd prefer that .. and your AI can check the docs and guide you.

Prefer to look yourself, the same data sits behind an app with charts and a full data dictionary.
tigzig.com → Tremor
and for human API docs, just hit the API link on top of the site.

Launched in March with around 50 indicators. Now with over 300 and new indicators being added regularly.

What is in it

331 public indicators across 8 categories:

Each indicator carries a notes field with the gotchas baked in. So when the AI pulls us_real_gdp, it sees the note saying it is already SAAR-annualized, do not multiply by 4. For in_nifty50_pe it sees the methodology break: standalone earnings before April 2021, consolidated after. For in_net_fdi it sees that negative means outflow and there is a 6+ month publication lag. That metadata lives in the API response, so the agent knows the sharp edges before it builds your analysis.

The pipeline

Three things worth knowing about how the data actually gets here.

One, we pull from APIs where available (FRED, RBI WSS, ECB Statistical Data Warehouse, OECD, Bundesbank, Bank of England). Where the data lives in a spreadsheet or a published file that changes format year to year (NCUA 5300 Call Reports, FDIC SDI aggregates, NY Fed Household Debt Study, MoSPI eSankhyiki, RBI DBIE Excel, Shiller's ie_data.xls, Manheim MUVVI), we download the file, parse it with error correction, and standardize it into a series. This runs automatically on a schedule.

Two, we run this three times a day. If the Fed publishes at 3pm ET, we pick it up in the next cycle and it is live in Tremor by early evening. India series update at their own cadences: RBI is a mix (repo rate, G-sec 10Y, 91-day T-bill and forex reserves are weekly; bank credit, aggregate deposits and M3 are fortnightly; trade balance, net FDI, net FPI and YoY growth series are monthly), MoSPI is monthly or quarterly depending on the series, NSE Nifty PE/PB is daily. Whatever the source cadence, we grab it as soon as it lands. Quarterly data (GDP, GFCF, and the credit-union aggregates) lands once a quarter and gets ingested the day it is published.

Three, the pipeline itself does error checking. Sums validate. Year-over-year calculations are consistent. If there is a data quality issue (a missing value, a sudden spike that does not match the source document), we flag it in the metadata and you can see it before you use it.

Sources at a glance

What moved recently

Tremor - Ask your AI to explore - one-pager overview

Working on something similar? How I work covers the rates, the availability and what I take on.