by mensfeld · Agent Tool · ★ 582
code-on-incus () Isolated machines for AI coding agents - with active defense. COI gives each AI agent its own machine - a full system container with root access, systemd, Docker, and the ability to install anything. Agents work like they would on a real server: run services, manage packages, use cron - without touching your actual system. Files stay correctly owned, no permission hacks needed. Your credentials stay on the host. SSH keys, environment variables, and Git tokens are never exposed to AI tools unless you explicitly mount them.
| Stars | 582 |
| Forks | 47 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.4646781679776/100 |
| Open Issues | 21 |
| Last Updated | 2026-07-08 |
| Created | 2026-01-07 |
| Platforms | claude-code, cli, docker, python |
| Est. Tokens | ~20k |
These tools work well together with code-on-incus for enhanced workflows:
Explore other popular agent tool tools:
code-on-incus is Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. It is categorized as a Agent Tool with 582 GitHub stars.
code-on-incus is primarily written in Python. It covers topics such as agentic-ai, ai-tools, anthropic.
You can find installation instructions and usage details in the code-on-incus GitHub repository at github.com/mensfeld/code-on-incus. The project has 582 stars and 47 forks, indicating an active community.
code-on-incus is released under the MIT license, making it free to use and modify according to the license terms.