Skip to content

DEV Community

amabito

Writing veronica-core -- runtime cost containment for LLM agents. RTX 5090 / CUDA 12.8 / Python.

Japan Joined on Feb 23, 2026 https://github.com/amabito/veronica-core

amabito

Mar 9

The $0.64 bug: how nested retries silently multiply your LLM costs

#python #llm #langchain #ai

5 min read

amabito

Feb 23

The $12K Weekend: What Nobody Tells You About LLM Agents in Production

#ai #opensource #llm

4 min read

loading...