head to head · open source
AI-Infra-Guard vs code-on-incus
AI-Infra-Guard has 6,471 GitHub stars, 599 forks, 35 open issues and last shipped today. code-on-incus has 726 stars, 63 forks, 24 open issues and last shipped yesterday. AI-Infra-Guard leads on adoption by 791% (6,471 vs 726 stars). AI-Infra-Guard is written in Python under Apache-2.0; code-on-incus is written in Go under MIT. AI-Infra-Guard has attracted 9% as many forks as stars, code-on-incus 9%. AI-Infra-Guard was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (agentic-ai), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| AI-Infra-Guard | code-on-incus | |
|---|---|---|
| GitHub stars | ★ 6.5K | ★ 726 |
| License | Apache-2.0 | MIT |
| Written in | Python | Go |
| Last push | 2026-09-20 | 2026-09-19 |
| Forks | ⑂ 599 | ⑂ 63 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick AI-Infra-Guard if
- You weight community size — 6.5K stars and counting
- You want the Apache-2.0 license terms
- Your stack matches Python
- You value the larger contributor base for long-term maintenance
pick code-on-incus if
- You want the code-on-incus feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Go
- You evaluated both and code-on-incus fits your workflow better
About AI-Infra-Guard
AI Infra Guard (A.I.G) is a full stack AI red teaming platform from Tencent Zhuque Lab that scans agents, MCP servers, agent skills and AI infrastructure for security risk and evaluates large language models against jailbreak attacks, built for security engineers and AI platform teams that need to self examine their own AI deployments.
read the full AI-Infra-Guard overview →
About code-on-incus
code on incus (coi) is an MIT licensed Go tool that runs AI coding agents such as Claude Code, Codex, opencode, pi, and omp inside their own isolated Incus system containers — full Linux machines with root, systemd, and Docker — and adds kernel level active defense that pauses or kills the container when it detects dangerous behavior, for developers who need real machine access without exposing the host or their credentials.
read the full code-on-incus overview →
More in AI & Machine Learning
Related comparisons
More AI Security & Privacy projects
Compare either of these against the rest of the AI Security & Privacy field.
Frequently asked questions
Is AI-Infra-Guard or code-on-incus more popular?
AI-Infra-Guard has 6,471 GitHub stars and code-on-incus has 726. AI-Infra-Guard has the larger community by that measure.
Are AI-Infra-Guard and code-on-incus free?
Both are open source. AI-Infra-Guard is licensed under Apache-2.0 and code-on-incus under MIT. Neither carries a licence fee.
What is the difference between AI-Infra-Guard and code-on-incus?
AI-Infra-Guard is written in Python and code-on-incus in Go. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, AI-Infra-Guard or code-on-incus?
Choose AI-Infra-Guard if you want the larger community (6,471 stars) or its Apache-2.0 licence terms. Choose code-on-incus if its feature set, stack or MIT licence fits better. Both are self-hostable.