Koala runs ARM64 Linux virtual machines on Apple silicon Macs, one VM per job, service, development environment or AI agent. Each VM gets its own kernel, disk and network and only the access you grant it, and VMs can stay up after the terminal closes. It installs through Homebrew, needs Apple silicon on macOS 26 or later, and is currently at a 0.1.0 preview.
Be the first to rate Koala. Your feedback helps other users decide.
Start a VM, execute a command inside it and read the output.
Create a VM that stays running after the terminal session closes.
Give an agent its own VM with its own kernel and network access.
Similar tools in the same category โ compare side-by-side
Jevstiller distils a hosted model into a local one that answers like it. A local model is trained to...
Luke is a macOS app for planning with a coding agent by voice. You talk through a feature, it reads ...
LLM Fuzz CI is a GitHub Action that lets a coding agent attack the tests you wrote. The agent reads ...
Guides and comparisons about code tools
Nine launches that keep work on your own hardware: a model storage server, offline file search, native dictation, ARM64 VMs and a single-binary coding agent.
Ten Hacker News launches that treat agent context, persistent memory and token accounting as first-class problems instead of afterthoughts.
Eleven recent open-source and self-hosted projects for building, sandboxing and deploying coding agents you own outright rather than rent.
Eleven recent projects that turn the Model Context Protocol from a neat demo into deployable infrastructure: registries, compiled servers, and gateways.
Eleven recent open-source projects for running inference, transcription, deep research and security work entirely on hardware you control.