Groundline is the trust layer between your documents, your data, and your AI agents - on your desktop, or across your team. Drop in the files behind a report and it finds the claims, links every number to its evidence, and flags what no longer holds.
Download for Windows · macOS (Apple Silicon) · macOS (Intel) · Linux (.deb) - native app, not a browser in a trench coat. Deploying for a team?
Free, with every feature.·Your files never leave your machine.·No account, no key, nothing phones home.
The questions every review quietly worries about -
Groundline detects the claims your documents make and matches each figure against the values in your spreadsheets and data files - exact and approximate matches honestly labeled, unsupported numbers called out.
Deterministic checks raise concrete, explainable findings - contradictions between documents, formulas silently replaced by typed values, charts drawing on hidden rows, causal language resting on correlation.
Summary!C9 contains a hardcoded 1,860,000 - neighbouring cells still compute =SUM(...).Upload a newer copy of a file and Groundline explains what changed in business terms - then flags every downstream slide, paragraph, and recommendation still carrying the old numbers, with a reviewable correction attached.
An MCP server exposes the workspace to Claude, ChatGPT, or your coding agent as structured tools. Agents can trace numbers, validate claims, and propose corrections - every proposal lands in the human review queue.
groundline_validate_claim and groundline_trace_number◆ agent calls groundline_validate_claim { "claim": "Revenue grew 24% in Q2 2025" } ◇ groundline responds { "support": "outdated", "evidence": "Revenue!D14 = 18.7% (v3, current)", "was": "24.0% in v2", "proposal": "queued for human review" } - no silent edits. ever.
Not just the text - the formulas, the hidden rows, the speaker notes, the chart source ranges, the metadata. 29 formats, from an .xlsx to a .parquet to a scanned .png.
Formulas & cached values, hidden rows/columns/sheets, merged cells, charts and their source ranges, named ranges. Flags hardcoded formulas, broken references, totals that don't add up.
Delimiter & encoding detection, per-column types and stats. Flags duplicate and near-duplicate rows, identifier collisions, category spelling drift, date gaps, suspicious rounding.
Slides, titles, body text, speaker notes, tables, chart data, hyperlinks - and embedded pictures via optional local OCR. Flags duplicate slides, truncated axes, charts without readable data.
Headings, paragraphs, tables, hyperlinks, metadata - and embedded pictures via optional local OCR. Detects claims per paragraph and flags causal language for review.
Page text and tables (best effort), metadata. Detects image-only pages and suggests local OCR - an on-device model reads them without the file leaving your machine; reports password-protected files as locked. Audit reports export back out as PDF.
Headings, paragraphs, lists, tables, links. Claims and assumptions extracted like any other source.
Flattened into the same rows and columns the CSV path profiles - or field → value when the structure isn't tabular - so they get the same duplicate, collision and correlation checks.
Converted to text with tables preserved as real tables. An email's subject line is analyzed too - it's very often where the headline number lives.
Read with local OCR: nothing leaves your machine. Recovered text is labeled as OCR and its claims carry lower confidence, because it's a reading of a picture, not a value from a file.
Legacy Office and OpenDocument files are converted by LibreOffice and then read by the extractor for the modern format - one parser family, not four. If it isn't installed, the app says so by name instead of failing with a vague parse error.
Claim detection reads English, Portuguese, Spanish, German and French, and numbers are read in both decimal conventions - so a European figure never arrives silently a thousand times too small.
1.234), the document's own convention decides it - detected once per file€1.234, 1.234,56 EUR)Q3, T3, H1, FY 2026, 2. Quartal, 1º trimestreFiles don't only arrive by drag-and-drop. Watch a synced folder, read a query straight out of PostgreSQL, and re-check a workspace on a schedule instead of only when someone touches a file.
READ ONLY transaction, capped by row count, with the connection string sealed at rest and never returned to the browserThere is no paid tier, no license key, no trial and no seat limit - every feature below is in every install. The only thing to decide is whether you are running it for yourself or for a team, because the setup differs.
A native window with the analysis service bundled inside. No Docker, no terminal, no account - your files never leave the machine.
On a Mac the button gives you the Apple Silicon build. If yours is an Intel Mac - anything sold before late 2020 - take the Intel build instead; the two are not interchangeable.
Windows · macOS · macOS (Intel) · Linux (.deb) - it updates itself from then on. Prefer to build it? Clone the repo.
The same app served to your network, with accounts and one shared review queue. Your git repository is the control plane, so nothing leaves your infrastructure either.
docker compose up -d.GROUNDLINE_ALLOWED_HOSTS to your hostname and put TLS in front. That switch - not a license - is what turns accounts on.A desktop or localhost install stays single-user with no login screen, deliberately - accounts appear only when you serve a network host.
Nothing here is held back, metered or time-limited, and nothing phones home. No account is created anywhere, because there is nowhere to create one.
AGPL-3.0 - open source that stays open: nobody can sell a closed fork or a proprietary hosted copy. Local-first by design: a native desktop shell, a deterministic analysis pipeline, SQLite on your disk. A seeded demo workspace - with deliberately planted issues - shows every feature on first launch.
$ git clone https://github.com/guilhermecariru/GroundLineOSS $ cd groundline && npm install $ npm run tauri dev ✓ analysis pipeline ready · deterministic ✓ desktop Groundline running · native window ✓ seeded demo workspace “Quarterly Business Review” └─ planted: outdated deck, contradictory slide, hardcoded formula, duplicate records, causal claim…
Free, open source, and honest about what it can't do. Install it, drop in the files behind your next report, and see what holds.
Direct downloads: Windows · macOS (Apple Silicon) · macOS (Intel) · Linux (.deb) - new releases and changelogs: follow on GitHub.
Windows will warn you on first run: only the Linux builds are code-signed today. Windows shows “Windows protected your PC” (More info → Run anyway); macOS needs a right-click → Open once. Signing certificates cost money the project doesn't take in - nothing about the app changes either way.