Mantis
Open-source agent operations, security, and governance for multi agent, code agent, security.
What does this agent do, and when should you use it?
The repository describes Mantis as: A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities. This profile is a source-based catalog entry; an independent FARS review is still pending.
A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
- Evaluate controls for operating or governing agent workloads.
- Test observability, security, or deployment behavior in a sandbox.
- Integrate documented controls into an existing operations stack.
What are this agent's strengths and limitations?
- Public source and README are available for inspection.
- Focused on multi agent, code agent, security.
- Setup, model-provider support, and maturity must be confirmed against the current release.
- No independent FARS score has been assigned yet.
How do you install or deploy this agent?
Follow the current installation instructions in the [repository README](https://github.com/google/mantis#readme). Requirements and provider setup vary by release.
How do you use this agent?
Start with the examples and quickstart in the [repository documentation](https://github.com/google/mantis#readme), then test the workflow with limited permissions and non-sensitive data.