All activity
Zafar Takhirovleft a comment
Hey Product Hunt - I built AgentDbg because "agent debugging" was frustrating: when something loops, stalls, or calls a tool with the wrong args, I want a debugger, not a dashboard. AgentDbg runs entirely locally: traces are JSONL files on disk, and the viewer is a local web UI. v0.1 includes loop warnings, (best-effort) redaction by default, `@trace` / `traced_run`, and an optional...
AgentDbgDebug everything your AI Agent does, locally