Already installed Rivloom? Start with model setup. To connect another computer, see device collaboration.
1 Install and open Rivloom
Visit the Download app page for the Windows x64 installer. Check the version, file size, and SHA-256 against the details on that page. Run the installer, follow the installation wizard, then open Rivloom.
The current installer is unsigned, so Windows may display a source or reputation warning. Check the file source and verification details before deciding whether to proceed. Runtime components are bundled; you still need any tools required by your project and network access to your model service.
2 Configure a model
Open Models & quota in the sidebar, configure an available model, and set defaults. Tasks use the execution device's account quota, and model calls may be billed.
3 Choose a working folder
Select New conversation, choose or add an ordinary folder below the input area, then select a model. Start with a test project that contains no sensitive information. Git is not required.
4 Choose an approval mode
Open Conversation settings, choose an AI approval mode, and add acceptance criteria if needed. For your first task, choose Request approval to review edits, commands, and network requests before continuing. See the security guide.
5 Describe your task and send it
Describe the goal, what may be changed, and how to check the result. The task enters the execution queue and starts when ready. Here is a request to try in a test project:
Read this project, document the steps for running it locally, and write them to GETTING-STARTED.md. Do not change other files. Explain any uncertainty. When finished, tell me what you wrote and which steps still need manual verification.
6 Review and confirm the result
Handle approvals and questions in the conversation. When the task awaits review, open the actual files, check the contents and necessary tests, then select Confirm completion. The engine's diff may not include every change; you still need to verify the files yourself.
Hand work to another device
Check the pairing details in Nodes & Brain on both devices and confirm trust separately. The receiving device first configures its own projects, models, and execution capability. Then, in a new conversation on the originating device, type @ and select it. Delivery, queue, and result receipts return to the original conversation.
Tasks from paired devices are received automatically and may consume the receiving device's model quota. Pair only with trusted devices. Device pairing and AI operation approval are separate confirmations.