Vertical AI · Startup idea
TurboTax owns the consumer. Nobody owns the small accountant who files for 200 clients a year — and the agent that does 30% of the data-entry work wins them.
Why now
1099 + W-2 + state form OCR is solved. The remaining work is the workflow on top — collecting docs, asking the right questions, drafting the return. Intuit ProConnect is mediocre; the indie tax preparer is hungry.
The idea you could build today
A doc-collection chat for the client (texts, emails, uploads), an OCR + classification pipeline on the prep side, and a generated draft of the federal + state return. Preparer reviews + files. Bill per filed return.
Build stack
The three repos already trying
No repos in the current period have crossed our minimum-volume + sector match for this idea. That can mean two things — the niche is too new for public GitHub signal to show up yet, or the buildable wedge is genuinely greenfield. Either way, watch this page; matches refresh weekly.
Matched against the current-period startup signal panel (fintech, ai-ml). Rankings shift weekly as the underlying GitHub activity moves. Read the methodology.
The seed-round pattern hiding in the trendline
Tax-OSS repos that integrate IRS form parsing with an LLM-classification layer hit the seed-stage tell.
Consumer-direct. The buyer here is the small CPA / EA who files 200 returns a year. Different motion, different pricing, different product.
Use the signal, not just the idea
The repos above re-rank automatically as commit velocity, contributor growth, and new-repo creation move. Want the data feed for this idea wired into your own stack? The MCP server exposes every signal as a tool any agent host can query.
Updated 2026-07-14. The framing is editorial; the “three repos already trying” slot is generated from the live signal panel. Anonymity rule: we name public GitHub orgs, never individual founders or stealth teams.