Blog
Practical notes on running AI agents as a production service with HiveGate. Every endpoint and snippet comes from the source, so you can check it.
-
LLM token usage and cost tracking per user and tenant
Record the tokens and USD cost of every model call your agents make, query it by user, tenant or agent, and cut Claude input costs with prompt caching.
-
Per-user Google and Microsoft OAuth for AI agents
How an AI agent can read and send from each user's own Gmail, Outlook and calendar: encrypted per-user token storage, automatic refresh, and toolkits.
-
Human approval before risky agent tool calls
Pause an AI agent before it sends an email or deletes data, let a person approve, edit or deny the call over a REST API, and keep a record of the decision.
-
Deploying Agno agents to production as a REST API
How to serve Agno agents over HTTP with per-user sessions, Postgres-backed history, API keys and a one-click Docker deploy, and when AgentOS is enough.