We're just getting started! Our roadmap includes more integrations, support for additional AI agents, and sandbox backends

🧑‍🚀 Join our Discord discord.gg/VGzGVWxrXz
💫 Star us on GitHub github.com/endorhq/rover

Big thanks to Ben for contributing key features to v2.0 🧑‍🚀:

- Hooks: run scripts on task completion, merge, or push
- GitHub issue tracking with --from-github
- Sandbox network allowlists
- File exclusion patterns for sensitive and non-relevant files

github.com/endorhq/rove...

Create custom workflows tailored to your projects: security reviews, compliance checks, documentation standards, and any process you want agents to follow consistently.

You can learn how to write your first workflow on docs.endor.dev/rover/guides...

These days, working on multiple projects is the norm. In v2, you can list, inspect, create and merge coding tasks in multiple projects at the same time. Forget about having a shell per project.

rover list --project my-app

Coding agents behave differently even under the same workflow. Each agent has its own strengths, weaknesses, and coding style.

Use the --agent flag multiple times in rover task and Rover will spawn one task per agent so you can easily compare their solutions.

Often, agents finish 90-95% of your request, leaving some minor follow-up changes. Running a full workflow process might be unnecessary, as agents can complete these little tasks in a single prompt.

Now, you can iterate tasks interactively.

The new VSCode extension adds support for additional workflows, like the tech-writer. Run tasks and monitor them directly from VSCode while you stay focused on your main work

Let Rover manage your agents in the background

From v1.6, your agents have access to multiple Alpine package repositories through our Package Manager MCP server. Agents can install software from a trusted source on demand.

We’ve used this to bump old projects to newer versions while ensuring everything works properly

github.com/Angelmmiguel...

Rover aims to work with your existing coding agent setup, so it needs to work across different environments. Some Rover users in corporate environments have reported issues running agents like Claude Code using third-party AI services, such as Google Vertex AI

A workflow is a powerful tool for coding agents. Providing clear steps to complete complex tasks usually leads to better results when you want agents to operate autonomously in the background.

In this version, we’ve developed the foundations of a new way to define workflows using YAML files

Version 1.2 introduces a new internal tool called rover-agent to manage the agents in the container sandbox. Previously, we were using plain scripts to initialize the environment, install the agent, configure it, and run the workflow to complete the task