WatchLLM – Debug AI agents step-by-step with cost attribution

Show HN: WatchLLM – Debug AI agents step-by-step with cost attribution

Based, WatchLLM – Debug AI agents step-by-step with cost attribution works in show hn launch.

Profile

Hi HN! I built WatchLLM to solve two problems I kept hitting while building AI agents:1. Debugging agents is painful - When your agent makes 20 tool calls and fails, good luck figuring out which decision was wrong. WatchLLM gives you a step-by-step timeline showing every decision, tool call, and model response with explanations for why the agent did what it did.2. Agent costs spiral fast - Agents love getting stuck in loops or calling expensive tools repeatedly. WatchLLM tracks cost per step and flags anomalies like "loop detected - same action repeated 3x, wasted $0.012" or "high cost step - $0.08 exceeds threshold".The core features:Timeline view of every agent decision with cost breakdown

The company sits in the show hn launch segment, where it competes on its core product or service.

It is recorded at the Show HN launch stage.

Website: watchllm.dev