Skip to content

BlockNext

BlockNext is a no-code platform for building and running AI-powered workflows. Design flows on a drag-and-drop canvas, connect AI models and third-party services, and let your automations run — no code required.

It is built for end users, not just developers: flows stay simple, readable and predictable by design.

Highlights

  • Visual flow builder — compose workflows on an intuitive drag-and-drop canvas. Flows are deliberately simple: no loops, no sub-workflows, no expression language to learn.
  • Describe it, don't configure it — give a node plain-language instructions and an LLM fills in its parameters at run time. Anything you set explicitly always wins over what the model infers.
  • Built-in MCP server — every integration node doubles as an MCP tool. Point Claude (or any MCP client) at your BlockNext server with an API key and use your connected services from chat.
  • AI-powered nodes — LLMs and generative AI (text, image, audio, video) as first-class building blocks, alongside integrations for the tools you already use.
  • Async done right — long-running AI jobs (video, music generation) are a single node. The node starts the job, polls the provider, and returns the finished result — no wait/check/loop scaffolding on your canvas.
  • Featherweight self-hosting — Go services on distroless images (15–32 MB each). The full stack idles around ~150 MB RAM (even less with TASK_RUNNER_MODE=embedded), each API sitting in single-digit megabytes. Runs comfortably on the smallest VPS.
  • Triggers — start flows manually, on a schedule, or from the outside via webhooks and API calls.
  • Live execution view — watch every task and node progress in real time over WebSocket.
  • Credentials management — encrypted at rest, OAuth tokens auto-refreshed, and only ever decrypted at execution time — flows never embed secrets.

Curious how it works under the hood? See the architecture overview.

Getting started

make setup      # creates .env with generated secrets
make docker-up  # pulls the published images and starts the full stack

Docker and make are all you need — Go and Bun are only required for development.

The UI is served on http://localhost:4000. Run make help for every target.

To build and run everything from source instead, see CONTRIBUTING.md — the development workflow uses make local-docker-up.

Community

License

BlockNext is licensed under the Apache License 2.0.

About

Open-source no-code platform for building and running AI-powered workflows — drag, drop, automate.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages