AI security stack is getting f...cking important 10 open-source GitHub projects for letting agents use real tools without giving them the keys to EVERYTHING 01 E2B ▸ github.com/e2b-dev/E2B → isolated sandboxes for agent execution 02 gVisor ▸ github.com/google/gvisor → sandbox untrusted workloads ISOLATE THE AGENT 03 Firecracker ▸ github.com/firecracker-micro… → lightweight microVM isolation 04 Kata Containers ▸ github.com/kata-containers/k… → containers with VM-level isolation CONTROL THE TOOLS 05 Open Policy Agent ▸ github.com/open-policy-agent… → policy checks before actions execute 06 Casbin ▸ github.com/casbin/casbin → permissions + access control PROTECT THE SECRETS 07 Infisical ▸ github.com/Infisical/infisic… → secrets management for AI infrastructure 08 SOPS ▸ github.com/getsops/sops → encrypted secrets inside repos WATCH WHAT HAPPENS 09 Falco ▸ github.com/falcosecurity/fal… → detect suspicious runtime behavior 10 Trivy ▸ github.com/aquasecurity/triv… → scan code + containers + infrastructure the security loop: request → permission → sandbox → tool → execute → inspect → allow / block → log 3 layers I'd actually build: agent: E2B → OPA → Casbin runtime: Firecracker → Falco → Trivy secrets: Infisical → SOPS and this is where it gets interesting: giving an AI agent more tools makes it more useful it also gives it more ways to break something the next agent stack isn't just memory + tools + reasoning it needs permissions ⭣