Show HN: FactIQ – a realtime econ+finance database for AI agents
TL;DR
FactIQ is a new defog-ai plugin that aims to give AI agents direct access to a normalized real-time database for macro, finance and company data. The repo says the warehouse covers sources such as SEC filings, BLS, BEA, Census, EIA, USDA, IMF, World Bank, plus data from China, India, South Korea and Singapore. Agents can discover datasets, fetch series, run read-only SQL, use market and earnings data, and turn results into charts, reports or local HTML visualizations.
Nauti's Take
This is a sensible problem to attack, but it is not a Bloomberg replacement yet. The value depends on coverage, data quality, latency, historical revisions and clearly documented caveats.
The good part: read-only SQL, OAuth and a simple three-table model are pragmatic for agents. The pitch gets PR-heavy when it jumps to investment research automation while the repo still has few usage signals, no releases and limited public proof.
Briefingshow
For AI agents doing financial analysis, the bottleneck is often not calculation but finding, cleaning and reconciling data from fragmented sources. FactIQ attacks that layer by normalizing macro and market data into a shared schema. The MCP angle matters because it puts data access inside agent workflows instead of forcing analysts back into separate BI or terminal tools.
Sources