AIGCLISTAIGCLIST
Dyad
AI Tool Scorecard

Dyad

A free, open-source AI app builder that runs locally on your computer, supporting multiple AI models through bring-your-own API keys — positioned as a no-lock-in alternative to cloud-based platforms like v0, Lovable, and Bolt.new.

FreemiumAI App Builderdyad.sh
Visit
Published on Jul 6, 2026

Benchmarks

How Dyad scores on agent readiness and AI visibility AI Readiness and GEO Score are platform assessments generated by VibeLaunch after submission.

Powered by AIGC List Benchmarks

Decision summary

Developers building web applications with AI assistance

AI-assisted web app development with local execution

Best for

  • Developers who want AI-assisted coding without vendor lock-in
  • Rapid prototyping of JavaScript web apps
  • Teams that prefer BYO AI API keys

Watch out for

  • Testing panel is experimental and not production-grade
  • Requires separate AI API key setup before use
  • Limited to local development — no browser-based IDE

Overview

Dyad is a free, open-source AI App Builder that runs locally on your computer rather than in the cloud. According to its official documentation, it positions itself as an alternative to cloud-based platforms like v0, Lovable, and Bolt.new — with the key differentiator being local execution and no vendor lock-in.

How It Works

Dyad is a downloadable desktop application. After installing it, users connect their own AI API keys — the documentation recommends starting with Google Gemini's free tier, which the vendor states offers approximately 250 messages per day on Gemini 2.5 Flash. Anthropic Claude and OpenAI are also supported. Because you bring your own keys, you control your AI usage and costs directly.

The app builder targets JavaScript web applications. Once you've built an app with AI assistance, you push your code to GitHub and deploy through Vercel, which automatically detects your framework (such as Vite) and handles deployment with minimal configuration. The official documentation describes this GitHub-to-Vercel pipeline as the recommended path to production.

What's New in v1.7.0

The latest release (v1.7.0) focuses on stability and performance, particularly for larger apps. Memory usage has been bounded across several subsystems: chat attachments, voice-to-text recordings, preview console logs, and child-process output. These changes aim to prevent crashes during memory-heavy workflows like editing large files or running complex builds.

The standout addition is an experimental Testing panel for AI-generated end-to-end testing. You can use it to have AI help create tests for important user flows, making it easier to verify that your app still behaves as expected after changes. The documentation is clear about the panel's status: it is experimental and should be used as an aid alongside manual review — not as a replacement for thorough QA.

Who It's For

Dyad suits developers who want AI-assisted coding but prefer to keep their workflow local and under their control. It's a practical choice if you're comfortable managing your own API keys, deploying through Git-based pipelines, and working within the JavaScript ecosystem. Compared to cloud-based Low Code Platforms Directory, Dyad's local-first approach offers more control at the cost of requiring local setup and API key management.

The open-source license means you can inspect, modify, or contribute to the codebase — and the documentation explicitly mentions that users can collaborate on the open-source project or host private projects via GitHub. For teams that prioritize freedom from platform lock-in over the convenience of a fully managed cloud IDE, Dyad offers a credible path from local prototyping to Vercel deployment.

Reviews (0)

0 ratings

No reviews yet. Be the first to rate this product!

Score anatomy

The dimensions behind the editorial score, each with its judgment note. AI Readiness and GEO Score are platform assessments generated by VibeLaunch after submission.

Information quality

Documentation is clear and practical but entirely vendor-sourced. No third-party validation or independent benchmarks available.

6.5
Verify

Official docs provide step-by-step quickstart, release notes, and deployment guides. All claims originate from dyad.sh.

Ease of use

Quickstart guide is straightforward, but setup requires downloading the app and configuring separate AI API keys before any value is delivered.

7.0
Contextual

Quickstart walks through download → install → API key setup → first app. GitHub-to-Vercel deployment is described as requiring minimal configuration.

Feature depth

Core AI app building is solid. Testing panel is directionally valuable but experimental. Multi-model support provides flexibility.

7.2
Contextual

Supports Gemini, Claude, and OpenAI. v1.7.0 adds experimental testing panel and memory optimizations for large apps.

Workflow fit

GitHub + Vercel pipeline aligns with modern frontend deployment standards. Local execution may not suit teams preferring cloud IDEs.

7.5
Contextual

Documented GitHub-to-Vercel workflow with automatic Vite detection. Push-to-deploy model matches industry practice.

Reliability

v1.7.0 specifically targets stability and memory issues, suggesting earlier versions had reliability gaps. Testing panel is explicitly experimental.

6.5
Verify

Changelog details memory bounding across multiple subsystems. Testing panel documentation recommends continued manual review of important flows.

Value

Completely free and open-source. Users only pay for their own AI API usage. No platform fees or usage limits.

9.0
Strong signal

Documentation states Dyad is free and open-source. AI costs are user-managed via BYO API keys.

Scores indicate documented product strength, not a hands-on guarantee.

Agent Readiness

How well an agent can understand this product and reconstruct a documented workflow from its official information.

Automated agent-readiness assessment of https://dyad.sh/: 9 of 22 checks verified across 6 fetched pages. No substantial machine interface is documented — agents can understand and cite the product but not operate it. Absent: llms_txt, agent_tooling_artifacts, api_reference, request_examples, response_examples, error_documentation.

Readiness dimensions

DimensionScore
Documentation quality65
Execution verifiability0
Machine interface10
Project clarity100
Resource discoverability75
Workflow completeness80

What helps agents

  • docs: verified during this run
  • sitemap: verified during this run
  • quickstart: verified during this run
  • authentication: verified during this run
  • rate limits: verified during this run
  • version information: verified during this run

Where agents are blocked

  • llms.txt is absent (HTTP probe during this run).
  • No agent instruction files, code-distribution commands, or named slash-command skills found across fetched pages.
  • No api reference signal matched across 6 fetched pages.
  • No request examples signal matched across 6 fetched pages.
  • No response examples signal matched across 6 fetched pages.
  • No error documentation signal matched across 6 fetched pages.

Evidence check

Public claims about this tool, each tagged with a verification status and its cited source.

docs4
www.dyad.shVerifiedChecked Aug 30, 2026

Dyad is a free, open-source AI app builder that runs locally on the user's computer.

Dyad is positioned as an alternative to cloud-based AI app builders including v0, Lovable, and Bolt.new, emphasizing local execution and no lock-in.

Dyad is open-source, and users can collaborate on the project or host private projects via GitHub.

A documentation surface is reachable at https://dyad.sh/docs.

https://www.dyad.sh/docs
docs/getting-started/quickstart4
www.dyad.shVerifiedChecked Aug 30, 2026

Dyad supports AI models via user-provided API keys, including Google Gemini, Anthropic Claude, and OpenAI.

The vendor recommends starting with Google Gemini's free tier, citing approximately 250 messages per day on Gemini 2.5 Flash.

Users must download and install the Dyad desktop application to get started.

A quick-start / agent-skills documentation page is reachable at https://www.dyad.sh/docs/getting-started/quickstart.

https://www.dyad.sh/docs/getting-started/quickstart
docs/getting-started/publishing-your-app4
www.dyad.shVerifiedChecked Aug 30, 2026

Dyad apps can be deployed by pushing code to GitHub and importing the repository into Vercel, which auto-detects the framework (e.g., Vite) and handles deployment with minimal configuration.

Vercel is recommended as an excellent hosting option for Dyad-built JavaScript apps due to its easy setup and free plan.

Dyad is open-source, and users can collaborate on the project or host private projects via GitHub.

A quick-start / agent-skills documentation page is reachable at https://www.dyad.sh/docs/getting-started/publishing-your-app.

https://www.dyad.sh/docs/getting-started/publishing-your-app
docs/releases/1.7.04
www.dyad.shVerifiedChecked Jul 15, 2026

Dyad v1.7.0 includes an experimental Testing panel for AI-generated end-to-end testing of user flows.

The Testing panel uses AI to help create end-to-end tests for important user flows, making it easier to verify app behavior after changes.

The Testing panel is explicitly experimental and should be used as an aid alongside continued manual review of important flows before publishing.

Dyad v1.7.0 improved stability and performance for large apps and bounded memory usage across chat attachments, voice-to-text recordings, preview console logs, and child-process output.

https://www.dyad.sh/docs/releases/1.7.0
1.13.0 Beta 1 | Dyad2
dyad.shVerifiedChecked Aug 30, 2026

A documentation surface is reachable at https://dyad.sh/docs/releases/1.13.0-beta.1.

Agent-native positioning with a concrete operational path: "The release notes describe a concrete agentic loop in Build mode, which is an operational path for AI agents to work on apps.".

https://www.dyad.sh/docs/releases/1.13.0-beta.1
Dyad – Free, Local, Open-Source AI App Builder1
dyad.shVerifiedChecked Aug 30, 2026

The entry page was fetched and analyzed for machine-interface signals (title, headings, developer links, keyword probes).

https://www.dyad.sh/
https://www.dyad.sh/sitemap.xml1
dyad.shVerifiedChecked Aug 30, 2026

sitemap.xml is reachable and lists site pages.

https://www.dyad.sh/sitemap.xml
https://release-assets.githubusercontent.com/github-production-release-asset/964395174/aeb85193-e78b-4893-839f-6985cd0ceb51?sp=r&sv=2018-11-09&sr=b&spr=https&se=2026-08-30T13%3A22%3A54Z&rscd=attachmen1
dyad.shVerifiedChecked Aug 30, 2026

Decision desk

The questions most worth resolving before you rely on the product or visit its official site.

Dyad is a free, open-source AI app builder that runs locally on your computer. It helps developers build web applications using AI models like Gemini, Claude, and OpenAI through bring-your-own API keys.

Unlike cloud-based alternatives, Dyad runs entirely on your computer, giving you full control over your code and eliminating vendor lock-in. You can deploy your apps to standard cloud providers like Vercel via GitHub.

Dyad supports Google Gemini, Anthropic Claude, and OpenAI models. Users provide their own API keys, and Gemini's free tier (approximately 250 messages per day on Gemini 2.5 Flash) is recommended for getting started.

Push your code to GitHub, then import the repository into Vercel. Vercel automatically detects your framework (e.g., Vite) and handles deployment with minimal configuration. Environmental variables for API integrations can be added during or after deployment.

Yes, Dyad v1.7.0 includes an experimental Testing panel that uses AI to create end-to-end tests for important user flows. However, the vendor recommends using it as an aid alongside manual review — it is not yet a replacement for thorough QA.

Verify on official site

Continue exploring