Infrastructure & security
Run, observe and secure AI systems in production. 5 repos, most starred first.
strix
Strix runs teams of LLM-driven agents that probe your code, web app or API for vulnerabilities and try to confirm each one with a proof-of-concept. It suits developers who want pentest-style findings from a CLI or CI pipeline without static-scanner noise.
#2litellm
One OpenAI-style API and proxy server for calling 100+ LLM providers
#3NemoClaw
Reference stack for running AI agents inside NVIDIA OpenShell sandboxes
#4SkillSpector
Scans AI agent skills for security risks before you install them
#5CubeSandbox
Self-hosted MicroVM sandboxes for running AI agent code, compatible with the E2B SDK