opentakeoff

View on GitHub

Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. Rooms measured on the wall faces, symbol sweeps, materials + quantities with full provenance, built for preconstruction. Runs entirely in your browser.

★ 14461 forksTypeScriptApache-2.0Kentucky-ai

Apache-2.0 construction takeoff engine that measures quantities off PDF plan sets via a browser canvas or a 53-tool stdio MCP server (npx opentakeoff-mcp), with per-measurement scale, method and provenance so an agent's takeoff can be reviewed and exported.

Use Cases

Agent-driven quantity takeoff from construction plan PDFsAutomated room area measurement on wall facesFlooring and material quantity estimation from drawingsSetting sheet scale and calibrating measurementsSymbol sweeps and fixture counting on plansGenerating marked-up planset PDFsExtracting finish schedules and sheet-graph lookupsHuman review and correction of agent takeoffsConstruction cost estimating and preconstruction bidsRoll-goods seam layout for broadloom/sheet material

Built With

Language: TypeScript
Frameworks: Model Context Protocol SDK · PDF.js · Node.js · Vite · Docker · Python

opentakeoff

Use Cases

Built With

Tags