mantis
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
- adk
- adk-python
- ai-agents
- antigravity
- antigravity-cli
- application-security
- application-security-tools
- code-review
- devsecops
- gemini-api
- gemini-cli
- hardware-security
- llm
- multi-agent-systems
- prompt-engineering
- sast
- security
- static-analysis
- threat-modeling
- vulnerability-detection
- Stars
- 2,090
- Forks
- 179
- + today
- +10
- Created
- 3mo
Ranking data as of October 1, 2026 (UTC).
Overview
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities. It ranks #47 on GitTiger, gaining +10 stars on October 1, 2026 (UTC).
The project is written in Python and has 179 forks. It was created 3mo ago.
What it is
Mantis is a Python project described as a modular, stack-agnostic toolkit for AI coding agents. Its project description says the agents can autonomously find, reproduce, and patch vulnerabilities in software. The focus is on security work that can apply across different technology stacks.
Capabilities
The README preview describes reviewing a codebase’s history to identify past vulnerabilities that should not be repeated. It also mentions building a semantic index or code summaries to make code easier to work with. These are the specific workflows surfaced in the available preview; it does not provide further detail about how they operate.
Getting started
The available README preview does not provide a complete set of setup steps. Consult the Mantis README for current getting-started guidance.
git clone https://github.com/google/mantis.git
cd mantis
# see README for setupFrequently Asked Questions
What is Mantis for?
The project description presents it as a toolkit for AI coding agents to find, reproduce, and patch vulnerabilities.
What security workflows does the README preview mention?
Reviewing code history for past vulnerabilities and building a semantic index or code summaries.
Where can I find setup instructions?
Consult the README at https://github.com/google/mantis; the supplied preview does not give a complete set of setup steps.