Skip to content
CuttlelyCuttlelyCuttlely

Your first 10 minutes

You need Docker and one model key. The steps use OpenAI. Any chat model provider listed under Credentials works the same way.

  1. Get Cuttlely and start it:

    Terminal window
    git clone https://github.com/cuttlely/cuttlely.git
    cd cuttlely
    docker compose up -d

    Compose pulls the published Cuttlely image. If it cannot pull it, Compose builds the image from your checkout instead, which takes several minutes the first time, and each long build step says which of four it is. docker compose ps shows (health: starting) until Cuttlely is ready, then (healthy). Opening http://localhost:43117 early shows a Cuttlely is starting page that opens Cuttlely by itself.

  2. When it is up, the server prints a one-time setup link. Show it with:

    Terminal window
    docker compose logs cuttlely | grep "No account yet"

    Nothing yet? It is still starting. Run the command again in a few seconds.

  3. Open the link and create your account. The password needs at least 8 characters, including a lowercase letter, an uppercase letter, a digit and a special character. You are signed in and land on Chatflows.

  4. Try the demo. Chatflows shows a Try the demo card. Select Add a model key, choose OpenAI API, give it a name, paste the key, and select Add. The key is stored encrypted. Then select Try the demo: a ready-made bakery team opens with its chat open. Select the first starter question. The run card shows Harness Prime sending the work to the analyst, and a bar chart with the numbers from the made-up sales database appears in the chat. Try the demo shows each step.

    The bakery team’s test chat after the first starter question: the run card says Harness Prime sent work to analyst, then a bar chart of revenue by product and an answer with the top three products.

  5. Build your own team: open Harness · Agent Team, select New agent team, then Build with AI (the sparkle button). Your model and key are already picked under Chat model that builds. Pick one of the examples and select Build, then open the chat and select a starter question.

  6. Next time, sign in at http://localhost:43117/signin with Sign in.

Next: put a pipeline behind your team, give a specialist its own tables, or publish a chatflow. Docker settings, volumes and upgrades are in Docker. To change the code, use From source.