We vibe-coded a farm of Telegram agents in 2–3 days — here are the guts
A dev diary of a Telegram agent farm: cheap inference as layer zero, Hermes as the runtime, MCP for tool security — including the rakes we hit.
Read →Engineering blog
How we build and run agent systems on top of one OpenAI-compatible endpoint — architecture, tool security, and what it actually costs per month.
-
-
One router, three agents: how our support, admin and marketing bots share one cheap inference endpoint
Support, admin and marketing bots on one shared brain: an OpenAI-compatible router, a Hermes runtime and an MCP tool layer — the full architecture.
Read →