Governance layer for AI agents acting on infrastructure. Open source · Apache 2.0
About
MEHO is an open-source governance backplane for AI agents acting on infrastructure.
When AI agents can drain a node, rotate a credential, restart a service, or delete a namespace — you need more than a token and a hope. MEHO sits between your agents and your infrastructure, policy-gating every operation, issuing credentials just-in-time, and writing an immutable audit trail for every action taken.
Bring your own agent. MEHO governs what it's allowed to do.
Built in public by the team at evoila RDC. Shipping weekly.
Open source · Apache 2.0 · github.com/evoila/meho