Skip to the content
Open-source AI Security ReposPreview Test automation Learning Center

Part of the AI Security Learning Center Preview

Open-source AI security repos*

The GitHub projects people put to work for AI security: test it, guard it, scan it, run it.

Ranked by what GitHub reports, not by our opinion: stars, the last push, and whether the owners archived the project. The numbers are refreshed every morning. Each card says what the project is for, in plain words, and links to its security advisories and releases.

26projects, ranked within their group
7kinds of work, from red teaming to operations
318.4kstars between them on GitHub

Numbers as of 2026-11-18

The top ten by stars

Stars measure attention, not safety. Use them to find what many people rely on, then check it yourself.

  1. usestrix/strix76.5k
  2. aquasecurity/trivy39.5k
  3. gitleaks/gitleaks31.2k
  4. trufflesecurity/trufflehog29.5k
  5. promptfoo/promptfoo27.4k
  6. GreyDGL/PentestGPT16.5k
  7. anchore/grype13.3k
  8. Tracer-Cloud/opensre12.9k
  9. google/osv-scanner11.6k
  10. NVIDIA/garak10.1k

AI pentesting and offensive agents

Agents that attack your own applications, with your permission, to find what a real attacker would.

Red teaming and evals for AI

Test models and agents for prompt injection, jailbreaks and leaks, in a pipeline like any other test.

Guardrails and runtime protection

Checks that sit around a model or agent while it runs, on what goes in and what comes out.

MCP and agent scanners

Look inside MCP servers, agent skills and agent workflows before you connect them. The risks they look for are in the OWASP MCP Top 10. The OWASP MCP Top 10, explained.

Model files and the ML supply chain

Catch model files that run code when loaded, and prove where a model came from.

Check before you run: dependencies, secrets and SBOMs

The tools to point at any project on this page before you install it.

AI agents for operations

Agents that investigate production incidents for SRE and operations teams.

Archived: do not start new work on these

Their owners archived them, so they get no fixes. Listed because many guides still point to them.