Hi everyone, I’m Elia, the developer behind Denly.
Denly is a web dashboard for coordinating coding agents across projects. Its Cursor integration uses Cursor’s CLI on your own machine.
The workflow is:
- Submit a task for a project.
- Review the agent’s proposed plan and approve it.
- Let it build and run the checks configured for that repository.
- Review the resulting PR, request changes, or merge.
The dashboard brings together tasks waiting for approval, questions from agents, failures, and PRs ready for review. It also supports other coding-agent CLIs, so different projects can use different providers.
I originally started building around remote access. The part I’m focusing on now is coordinating work across projects and keeping track of where a person needs to step in.
The runner makes outbound requests to the control service; it doesn’t require opening a port on your machine. Your machine must be awake and online to execute tasks. Selected plans, transcripts, and other content can be uploaded, so local execution doesn’t mean everything stays local.
Denly has a free plan and paid tiers. You use your own agent account, with its existing limits and charges.
Product: https://denly.dev
Illustrated walkthrough with sample tasks: Coding-agent workflow demo: plan, recover and review | Denly
For people using Cursor across several repositories: how do you currently keep track of work that needs your attention? I’d appreciate feedback on whether this workflow helps.