MEHO

@Meho_ai

Governance layer for AI agents on infrastructure. Policy gates · short-lived credentials · immutable audit. Open source

Vienna, Austria

Pinned
MEHO
@Meho_ai
Sep 9
Introducing MEHO: the control layer for AI agents that touch real infrastructure. It decides what an agent may do, records every action it takes, and stops for a human when a step is risky. Open source, from evoila RDC. (1/12)
1
MEHO
@Meho_ai
Sep 24
1/ Our homemade fixes — CLI wrappers, a secrets vault, ticket discipline, inventory files — worked. For one operator, on one laptop. Then a second operator showed up. (6/12)
1
MEHO
@Meho_ai
Sep 21
1/ An AI agent with admin credentials can delete a datastore as easily as it lists one. For a while, nothing in our lab would have stopped it. (5/12)
1
MEHO
@Meho_ai
Sep 17
1/ To do anything useful, our agents needed admin credentials. Someone had to hand them over. That worried us — it should worry anyone. (4/12)
1
MEHO
@Meho_ai
Sep 14
1/ vCenter alone exposes ~3,000 REST API paths. That number ended our first idea about AI operations. (3/12)
1

MEHO’s posts