FileChomp
Turn piles of files into clean Excel sheets in seconds
FileChomp launched on May 24, 2026 with 2 votes, #6,288 of 20,538 launches that month.
What it does
Picture this: you’re a run-of-the-mill office worker. Barely a clue about AI. The day is nearly over, but a folder of invoices, forms, and PDFs still needs to become an Excel sheet. You’re tired, annoyed, and already dreading the copy-paste loop. FileChomp is for that moment: upload documents, say what data you need, and get a clean Excel file back. No sticky subscriptions. No soul-sucking enterprise setup. No complex prompting. No "10 file" limits. Files in, spreadsheet out.
Drop in PDFs and tell FileChomp what to extract. Get a clean Excel file back. Early beta: PDF → Excel only.
Preview release: PDF input → Excel output. More formats coming soon. Write naturally. Early beta supports PDF, DOCX and TXT input with an Excel output. Add files and an instruction, then start a job to generate your processed output. “ Extract names, invoice numbers, dates, and totals from these PDFs. ” “ Extract every table from these PDFs into one clean Excel workbook. ” “ Turn these receipt PDFs into rows of date, vendor, category, and amount. ” “ Extract party names, effective dates, term length, and renewal clauses from these contract PDFs. ” “ One row per PDF with a short summary, key findings, and recommended action. ” Most file work is repetitive but still too specific for normal…from filechomp.com
Does a similar job
all alternatives →
SnapSheets — PDF → Excel/CSV2025 · snap-pdfx-masimbamutyiri.replit.app · ▲7Instantly turn messy financial PDFs into clean Excel.

FileMergerDec 2025 · filemerger.online · ▲5Effortless Excel & CSV merging for clean, consistent outputs

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com