A.I.G (Tencent AI-Infra-Guard)
| Category | AI red teaming & evals |
|---|---|
| Official site | github.com/Tencent/AI-Infra-Guard |
| Maker | Tencent |
| Ownership / acquisition | Not published / not yet verified |
| License model | Open source |
| License | Apache-2.0 |
| Public pricing | Free (open source) |
| Source code | Tencent/AI-Infra-Guard |
| Last verified |
Facts are taken from the vendor's own site, GitHub, or a linked public source. Blank means we could not confirm it, not that it does not exist. Vendors can request a correction for free.
Lab result
Not yet tested. Lab testing is in preparation. No tool on the site has a lab result yet.
Similar tools
Comparison: The best AI red teaming tools in 2026: 16 compared
Comparison: MCP security scanners compared: 5 open-source tools
Frequently asked questions
What is A.I.G (Tencent AI-Infra-Guard)?
A.I.G (Tencent AI-Infra-Guard) is an open-source AI red teaming and evaluation tool from Tencent, released under the Apache-2.0 license. Open-source AI red teaming platform from Tencent Zhuque Lab that scans AI infrastructure for known CVEs, audits MCP servers and agent skills, red-teams agents and runs LLM jailbreak evaluations. Scanners also install on their own with pip. v4.6.9 (Nov 5, 2026) adds a CloudGPU provider preset for Agent-Scan, fixes MCP-Scan and Agent-Scan parsing issues, and removes third-party Agent-Scan provider presets. The project says the web platform has no authentication and should not be exposed on public networks.
Is A.I.G (Tencent AI-Infra-Guard) open source?
Yes. A.I.G (Tencent AI-Infra-Guard) is open source under the Apache-2.0 license. Source code: github.com/Tencent/AI-Infra-Guard.
How much does A.I.G (Tencent AI-Infra-Guard) cost?
Published pricing: Free (open source). Checked on November 6, 2026; confirm current prices on the official site.
Who makes A.I.G (Tencent AI-Infra-Guard)?
Tencent.
What are alternatives to A.I.G (Tencent AI-Infra-Guard)?
Other AI red teaming and eval tools listed here include Promptfoo, garak, PyRIT, Giskard and DeepTeam. See all 16 in AI red teaming & evals.