rover

We recently open-sourced Rover, a manager for AI coding agents. It is a tool we developed internally to help us work better with coding agents like Claude and Gemini. If you take a look at some of HN stories or tweets, it seems many developers are getting amazing results from coding agents while the rest of people are completely disappointed to the point of being a net negative. Think of Rover as the bundling of best practices and technical functionality (i.e. git worktrees) to have an easy way to interact better with coding agents. You can run multiple agents in the background and even combine them to complete a task. In practice, what this means is that: You can assign tasks to multiple agents and they can work independently and in parallel. The agents don’t interfere with each other or your system. They run inside containers and use gi

We have built Rover, an OSS tool that allows you to run multiple instances of Claude (and Codex, Gemini...) while keeping them from stepping on each other toes using containerized environments and Git worktrees https://github.com/endorhq/rover/

You can use Rover (disclaimer, I am one of the cofounders) which is an open source tool that you can use to parallelize the work of coding agents that in addition to Claude also works with Gemini, Codex and Qwen https://github.com/endorhq/rover/

This matches our experience developing with agents. In particular, as we wanted to use multiple agents in the background to do tasks, we had to really invest in different areas so they would not go in wild directions or have to ask continually for feedback, defeating the purpose of working in the background. First, we needed to provide relevant context on how to do the task (some of it is "generic" like Svelte documentation, some of it is specific to how to write tests for our particular project), be extremely detailed and specific in the prompt about what we want and how to go about it (divide it in different well defined steps) and finally provide with specific tools via MCP (like MySQL access and installing system packages). Once we consistently do all this work upfront, it really pays off because you can launch a large number of agent