AIToday
Large Language ModelsOpen-Source AIAI Business & IndustryHacker NewsPublished: Jul 22, 2026, 06:00 JST

OpenTakeoff: free, open-source tool lets AI agents measure building plans

OpenTakeoff: free, open-source tool lets AI agents measure building plans

3 Key Points

  1. What happened

    OpenTakeoff, a free open-source web tool for measuring quantities off building plans (called takeoffs), launched with a new feature in July 2026 — an MCP server that lets AI agents drive the measuring engine directly, accessing the same flood-fill room-tracing tool that human estimators use.

  2. Why it matters

    Until now, no open-source web-based takeoff canvas existed, and none built for AI agents. This tool lets both people and agents measure real building plans the same way, with every measurement recording its scale, method (one-click or hand-drawn), and who made it (person or agent) — creating an audit trail that travels with the number. For flooring and construction trades, it offers capabilities (like One-Click Area, waste %, and materials buy lists) that commercial tools charge $300/month to access.

  3. What to watch

    The MCP server (npx opentakeoff-mcp, on the official MCP registry, v0.2.0) lets agents browse the plan set natively — sheets, title-block text, and rendered pages as MCP resources. All data stays on your machine (browser-based storage); optional team cloud mode via Google Drive is available but off by default.

Not sure about something? Ask the AI

Summaries like this, in your inbox every morning.

Context & Analysis

OpenTakeoff addresses a long-standing gap: there has been no open-source, web-based takeoff canvas available to the construction and flooring trades at all. The tool originated as the takeoff module of a private flooring estimating app, then was extracted, cleaned up, and released as a genuine alternative — including the One-Click Area flood-fill tracer that commercial tools charge $300/month to provide. The measuring engine itself is production-grade, not a simplified demo.

The July 2026 addition of the MCP server is the key innovation for AI adoption. Until now, AI agents could not measure a real building plan the way an estimator does; OpenTakeoff is the first place they can. Because the same engine runs for both people and agents, every measurement carries provenance — the scale, whether it was one-click or hand-drawn, and whether a person or agent made it. This audit trail travels with the number, which matters for construction bids and accountability.

The tool's architecture keeps data local by default: PDFs and takeoffs never leave your machine, stored in browser IndexedDB and localStorage. An optional team cloud mode via Google Drive is available, but it is strictly additive and off by default. This design preserves the security and ownership benefits of a static site for users who want them.

FAQ
How do I use OpenTakeoff — do I need to install anything?
No installation required. Open the live demo page, drag in a building plan PDF or image, and start measuring. All data stays in your browser; no account, no upload, no server needed.
How can an AI agent use it?
In July 2026, an MCP server was added (npx opentakeoff-mcp, on the official MCP registry at v0.2.0). An AI agent can call the same measuring tools over MCP — one-click room tracing, area calculation, and others — and browse the plan set natively (sheets, text, rendered pages).
What can I measure with it?
Area, linear distance, count, and deduct measurements work on any takeoff — flooring, drywall, paint, concrete, sitework. The tool includes finish-aware features for flooring (conditions with CAD hatches, waste %, square-yard output, and materials buy lists with coverage rates).

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • SpaceX launches Grok 4.7 at $4.69 per task, beating rivalsSiliconANGLE AI · 2h ago
  • Amazon blocks Meta's Muse agent from its marketplaceSiliconANGLE AI · 2h ago
  • SyncLect Agent Garden turns Teams talks into AI knowledgeITmedia AI+ · 2h ago

AI-summarized, only the topics you pick — one digest a day via Email, LINE, or Slack.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleGoogle releases token-efficient Gemini models, cuts agent costs up to 65%