About Dafthunk

Dafthunk provides serverless visual workflow automation that lets users build workflows by connecting AI models, browsers, data pipelines and APIs, then deploy them on Cloudflare's serverless platform. The tool emphasizes that the entire stack is MIT licensed and runs on Cloudflare, with no enterprise tier or carved-out features. It targets developers who want to construct automated AI-enabled processes and data pipelines in a visual editor.

The platform offers a visual workflow editor built with React Flow, allowing users to drag and drop to create automation pipelines. Workflows run on Cloudflare Workers and Workflows, and are designed to require no infrastructure provisioning or containers. Durability is built in, so long workflows survive restarts and retries.

Dafthunk supports numerous capabilities across AI, browser automation, data processing, media, and integrations, enabling creation of AI-powered workflows, web scraping, and data transformations. It integrates with popular services and models, and provides a way to connect to REST APIs and third-party tools.

Open source and self-hosted, Dafthunk is MIT licensed with no enterprise tier and no fair-code restrictions. It provides source code on GitHub and can be forked, self-hosted, or embedded in other products. The project is developed publicly to explore AI-assisted development and its limits. The platform is designed to be deployed on Cloudflare, with ownership of data and deployment clearly stated.

Use cases

Automate AI-driven workflows
Scrape and process data from websites
Create media and content pipelines

Key features

Build AI workflow automation using multiple AI models such as Anthropic Claude, OpenAI GPT, and Google Gemini
Visual workflow editor for creating automation pipelines
Durable, serverless execution
Persistent storage for workflows
Triggers and queues for event-driven automation
Extensive integrations with popular platforms
Open source MIT license with no enterprise tier
Extensive node library and templates

Pros and cons

Pros

MIT-licensed, no enterprise tier

Serverless, scale-to-zero architectures on Cloudflare

Reviews

Loading reviews…

Frequently asked questions

What is Dafthunk?

Dafthunk is an open source visual workflow automation platform. You build workflows by connecting nodes in a React Flow editor, and they run as serverless workflows on Cloudflare Workers and Workflows, with state persisted in D1, R2, and Durable Objects.

Is Dafthunk free and open source?

Yes. Dafthunk is fully MIT licensed, with no enterprise tier, no fair-code restrictions, and no community edition that hides features. The entire workflow engine, node library, and runtime is on GitHub under the same permissive license.

How is Dafthunk different from n8n, Zapier, or Make?

Dafthunk is MIT licensed rather than fair-code like n8n, and it runs natively on Cloudflare's serverless platform. Workflows scale to zero when idle and scale up automatically with demand, with no containers or infrastructure to provision. You can self-host it for free or embed it in commercial products.

Do I need to manage servers or containers to run Dafthunk?

No. Workflows run on Cloudflare Workers and Workflows, so execution is serverless and durable by default. There is nothing to provision or scale. State is persisted in D1 SQL databases, R2 object storage, and Durable Objects, and long-running workflows survive restarts and retries automatically.

What kinds of workflows can I build with Dafthunk?

You can build AI workflows, web scraping and browser automation, data transformations, API integrations, scheduled cron jobs, webhook handlers, and email pipelines using 470+ nodes across AI models, browsers, data processing, media, and third-party integrations.

Can I self-host Dafthunk on my own Cloudflare account?

Yes. The full source is on GitHub and deploys to a standard Cloudflare account using Workers, Workflows, D1, R2, and the Workers AI and Analytics Engine bindings. You own your data, your deployment, and your costs.

Alternatives to Dafthunk

GPTConsole

GPTConsole provides autonomous AI agents for developers to build, test, and deploy production-ready apps using agents like Pixie and Chip.

Userdoc

Userdoc turns code and ideas into software specs, user stories, and acceptance criteria to help teams document and plan software with AI.

DiscuroAI

DiscuroAI defines and executes AI workflows for developers, enabling building, testing and consuming complex AI flows via a single API call.

GooseAI

GooseAI provides a fully managed NLP API service intended to reduce AI infrastructure costs for developers.

GitHub Copilot

GitHub Copilot is an AI coding agent integrated with GitHub to help write, understand, and ship software across development tasks.

LangChain

LangChain provides an open agent platform for building, deploying, and governing autonomous agents and observations, targeting teams that build AI-powered workflows.