OpenConstructionEstimate-DDC-CWICR
Open multilingual construction cost database and estimation pipeline for AI agents.
55K+ work items, 27K+ resources, and 30 regions with semantic search and n8n workflows.
OpenConstructionEstimate-DDC-CWICR provides a massive multilingual construction cost database structured for AI agents, complete with pre-computed embeddings and n8n workflows. It is built for developers and estimators integrating automated cost estimation into text, photo, and CAD pipelines.
What it is
The project organizes national cost bases across 30 regions into canonical 95-column schemas and compact resource catalogs, backed by Qdrant vector databases for semantic search. It includes n8n workflow templates for extracting estimates from Telegram messages, site photos via GPT-4 Vision, architectural PDFs, and CAD/BIM models.
Who it's for
It suits software developers building AI-powered construction estimation tools and professional cost estimators looking for structured multi-region rate data. It does not suit end users seeking a simple out-of-the-box cloud SaaS application without technical setup.
Key features
30 Regional Tracks
Pre-installed national cost bases including Berlin, Sydney, Zagreb, and global markets.
Semantic Search via Qdrant
Pre-computed vector snapshots and collections enable instant similarity search across 11 languages.
n8n Workflow Automation
Ready-to-use pipelines for calculating estimates from text chats, site photos, PDFs, and CAD exports.
85-Field Data Schema
Comprehensive structure detailing classification, resources, labor, and machinery norms.
OpenConstructionERP Integration
Open-source ERP that ships with this database pre-loaded for professional BoQ editing and 4D/5D planning.
Up and running in 3 steps
Our honest verdict
What's great
- Contains over 55,000 structured work items and 27,000 resources across 30 regional tracks.
- Includes pre-computed vector embeddings for immediate semantic search implementation.
- Comes with ready-made n8n workflows for text, photo, PDF, and BIM-based cost takeoff.
- Provided in standard tabular formats like Parquet, XLSX, and CSV alongside native language data.
Where it falls short
- Running the local desktop app requires Python and package installation via pip.
- Advanced workflows require setting up external services like n8n and Qdrant vector databases.
- Data is dual-licensed under CC BY-NC 4.0 for non-commercial use, restricting proprietary commercial deployments without a separate DDC license.
Pricing & license
The database and code are free under their respective open source and non-commercial licenses. There are no software license fees from the repository creators, though running automated pipelines requires your own compute, LLM API keys, and infrastructure.
Open remote AI-training roles
876 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
What data formats are available in the repository?
The national cost bases are provided in parquet and xlsx formats using a canonical 95-column schema, along with compact resource catalogs in csv and xlsx.
Can I use this database for commercial projects?
The data is licensed under CC BY-NC 4.0 for non-commercial use, and commercial usage requires a separate DataDrivenConstruction license while the code is Apache-2.0.
