· about 9 hours ago· Dev.to
How I Cut Agent Token Usage by 89% Without Touching the Agent
Every time your agent calls an LLM, it sends the full conversation history. Turn 20 includes turns 1–19. Turn 50 includes turns 1–49. Nobody notices because it's happening inside the agent, silently, on every single request. I noticed it while building Trooper - a Go proxy that sits between agents a
#cloud-computing#llm#agent-optimization#token-usage#machine-learning