Skip to content
BlockNext logoBlockNext logo

BlockNext

Build and run AI-powered workflows — no code required. Design flows on a drag-and-drop canvas, connect AI models and the services you already use, and let your automations run.

Deliberately simple flows

No loops, no sub-workflows, no expression language to learn. Flows stay readable and predictable — that constraint is a feature.

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.

Built-in MCP server

Every integration node doubles as an MCP tool. Point Claude (or any MCP client) at your BlockNext server and use your connected services from chat.

Secure credentials

Encrypted at rest, OAuth tokens auto-refreshed, and only ever decrypted at execution time — flows never embed secrets.

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.

A three-node flow on the BlockNext canvas: Starter → Anthropic Chat → Slack Send Message

Docker is the only prerequisite, on macOS, Linux or Windows alike. Three steps: get the code, generate the secrets in your .env, start the stack.

Terminal window
git clone https://github.com/blocknextai/blocknext.git
cd blocknext
make setup # writes .env with generated secrets
make docker-up # pulls the images and starts the stack

make targets are thin wrappers — make help lists them all, and the Quickstart gives the plain docker compose equivalent of each. The setup step copies .env.example to .env and gives every REPLACE_ME_OPENSSL_* placeholder its own generated secret; an existing .env is left untouched. Migrations run in a one-shot container before the services come up, so the first start takes a little longer.

Then open http://localhost:4000. The Quickstart walks through the same steps with more detail, plus what to do when you have no make.