What it is
Bidwright is an open-source construction estimating workspace for handling bids from intake and takeoff to pricing, review, and quote delivery. Estimators can work manually, ask AI to review an estimate, or have an agent draft line items for their review. PDF takeoff supports count, linear, area, and region annotations; 3D model takeoff extracts quantities and supports filtered bills of materials and revision comparisons. Viewers are listed for PDF, DOCX, XLSX, DWG/DXF, email files, Bluebeam markups, RTF, and ZIP. Its estimator library covers resources, ratebooks, assemblies, labor units, cost intelligence, playbooks, knowledge, and datasets. The desktop app stores data locally without a cloud account, and manual workflows can run without outbound AI calls. Docker deployments can run offline or air-gapped after setup. Desktop and Docker self-host plans are free; desktop AI is disabled until a user adds a key, and AI usage is billed by the provider. Hosted service is coming soon, with pricing not listed.
Who it suits. The desktop app is positioned for a solo estimator, owner-operator, or evaluator. Docker self-host is aimed at a small team or power user.
Good
- PDF takeoff supports four annotation types
- 3D takeoff extracts model quantities
- Desktop stores data locally
- Manual estimating can run without AI calls
- Free desktop and Docker self-host plans
Watch for
- Desktop AI requires the user's own key
- AI usage is billed by the provider
- Hosted service is coming soon
- Docker self-host support is through GitHub Issues
Verdict
Bidwright combines estimating, takeoff, bid management, and review workflows, with both local desktop and self-hosted options. Users should account for provider-billed AI and the separate setup and support model for Docker.
Plans and prices
| Plan | Price | Billed |
|---|---|---|
| Desktop app | $0 | Free/download |
| Docker self-host | $0 | Free under AGPL-3.0 |
| Hosted | — | Coming soon; pricing will be published before general availability |
From Bidwright's own pricing page, checked 14 Oct 2026. Every plan
What the maker publishes
- 2D takeoff
- PDF takeoff supports calibrated count, linear, area and region annotations, symbol detection, region questions and PDF markup export. source
- 3D takeoff
- 3D workflows ingest IFC, Revit through Autodesk APS, DWG and Navisworks files, extract element quantities, create filtered BOMs and compare revisions. source
- AI billing
- AI usage is billed directly by the user's provider; Bidwright says it does not proxy or rebill tokens. source
- AI intake
- The agent can classify bid-package documents, create worksheets, take off symbols and draft cited line items while the user remains editor of record. source
- AI integrations
- Bidwright supports bring-your-own keys for Anthropic, OpenAI, OpenRouter, and Gemini, with local LM Studio and Ollama options also described. source
- AI integrations
- Bidwright accepts user keys for Anthropic, OpenAI, OpenRouter and Gemini, or local LM Studio with Ollama embeddings. source
- AI review
- Review combines rule-based quality checks with cited AI coverage, gap and risk findings that users can resolve, dismiss or defer. source
- AI workflows
- Users can estimate manually, have AI review an estimate, or let an agent draft line items for their review. source
- API and MCP
- The public repository describes a Fastify API, CLI endpoints under /api/cli/* and an MCP server exposing estimate, knowledge, model, quote, review, system and vision tools. source
- Data and security
- The desktop app stores data locally and does not require a cloud account; the site says organization AI keys are not visible to Bidwright. source
- Data control
- The site says desktop data stays on the machine, no cloud account is required, and local deployments can operate offline or air-gapped. source
- Desktop packaging
- Desktop releases are Electron bundles with embedded Postgres, API and web app for macOS DMG, Windows installer and Linux AppImage. source
- Documentation depth
- The repository includes setup documentation, Docker files, environment examples, API/web/worker apps and a monorepo development stack using Node.js 20+, pnpm 10+ and Docker Desktop. source
- Document support
- The workspace lists viewers for PDF, DOCX, XLSX, DWG/DXF, MSG/EML, Bluebeam markups, RTF, and ZIP files. source
- Document viewers
- The workspace lists viewers for PDF, DOCX, XLSX, DWG/DXF, MSG/EML, Bluebeam markups, RTF and ZIP files. source
- Estimating library
- The library contains resources, ratebooks, assemblies, tiered labor units, cost intelligence, estimator playbooks, knowledge and datasets. source
- Estimator library
- The library includes resources, ratebooks, assemblies, labor units, cost intelligence, estimator playbooks, knowledge, and datasets. source
- Extensibility
- The repository documents a plugin framework with auditable extensions plus provider adapters for several hosted and local models. source
Review
Bidwright is a construction estimating workspace for solo estimators and small teams willing to manage their own setup. Its takeoff and estimating breadth is appealing, but the current choice is local desktop or self-hosted Docker—not hosted service.
Overview
Bidwright follows a bid from intake through takeoff, pricing, review, and quote delivery, combining estimating with bid management and document viewers. Estimates can be built manually, reviewed with AI, or started from AI-drafted line items for an estimator to check. Keeping manual workflows separate from AI makes the product usable without sending outbound AI calls.
Its breadth should suit contractors who want takeoff, estimating resources, and bid workflows together. The trade-off is operational: desktop data stays on the local machine, while Docker users manage their own infrastructure and rely on GitHub Issues for community support.
Compare it with other construction estimating software and construction takeoff software.
Key features
Takeoff and document review
PDF takeoff handles count, linear, area, and region annotations; 3D model takeoff extracts element quantities and supports filtered bills of materials and revision differences. This gives estimators options across drawing-based and model-based work. Viewers cover PDF, DOCX, XLSX, DWG/DXF, MSG/EML, Bluebeam markups, RTF, and ZIP files, which can keep varied bid documents in the same workspace.
Estimating resources and AI
The estimator library brings together resources, ratebooks, assemblies, labor units, cost intelligence, playbooks, knowledge, and datasets. AI can review an estimate or draft line items, but the estimator remains responsible for review. Users connect their own Anthropic, OpenAI, OpenRouter, or Gemini keys, or use local LM Studio or Ollama; AI charges come from the chosen provider rather than Bidwright.
Local operation and licensing
The desktop app stores data locally and requires no cloud account. The site says Docker deployments can run offline or air-gapped after setup. Organization AI keys are not visible to Bidwright. SaaS vendors embedding the AGPL product must offer source to users; those needing different terms are directed to ask about a commercial license.
Pricing
Both currently described plans cost 0.00 USD per free. The Desktop app is single-user for macOS, Windows, and Linux, with AI disabled until the user adds a key. It fits an individual estimator, owner-operator, or evaluator; it gives up multi-user server access.
Docker self-host is also 0.00 USD per free, under AGPL-3.0, and supports a multi-user server on self-managed infrastructure. It is the better fit for a small team or power user able to handle deployment and ongoing administration. Community support is through GitHub Issues.
Hosted is coming soon, with a waitlist open and custom pricing to be published before general availability. SSO, audit logs, and data residency are planned rather than current hosted controls.
Platforms
Bidwright spans macOS, Windows, Linux, web, API, and self-hosted use, with a hybrid desktop and server approach. Manual work can run without outbound AI calls; Docker's offline or air-gapped use applies after setup.
Who it's for
Choose the desktop app for one estimator who values local storage and can work without built-in AI until adding a provider key. Choose Docker when multiple users need a shared server and the team can own its infrastructure. It is a weaker fit for contractors who want a ready-to-use hosted service or included AI billing.
Pros and cons
- Pro: PDF and 3D takeoff, estimating resources, and bid management sit in one workflow, reducing the need to split those tasks across separate tools.
- Pro: Local desktop storage and manual workflows without AI calls suit users who want to work without a cloud account or AI dependency.
- Con: Docker's self-managed infrastructure and community-only support put setup and operations on the team.
- Con: AI requires the user's own provider key and is billed by that provider, so AI is not an included, bundled service.
- Con: Hosted controls remain planned, leaving teams seeking managed access without a current hosted option.
Alternatives
Choose OpenConstructionERP instead if a self-hosted AGPL platform with 120,000+ cost items and 190+ modules better fits the job; its free plan also has community support.
Buildxact is worth considering for mobile and web access with complimentary credits, AI estimating, professional proposals, and Home Depot material ordering; its Foundation plan is 169.00 USD per month.
Choose Cubit Estimating if a paid Windows or web option with a free trial fits better; its AI Estimating add-on is 20.00 AUD per month per user at an early-adopter price for a limited time.
STACK may suit a team that wants a free web and mobile takeoff plan with a defined cap of one active project per month, 300 plan pages, 50 measurements per project, and one viewer seat.
Consider QuoteSoft, ConEst IntelliBid, CostX, or SharpeSoft Estimator as alternatives if Bidwright's deployment model does not fit.
Verdict
Bidwright is a strong candidate for solo estimators and technically capable small teams who want broad takeoff and estimating workflows without paying a software subscription. Choose it for local desktop use or a team-managed Docker server; look elsewhere if you need managed hosting, bundled AI, or vendor-led setup and support.