agent-inspect

Local execution trees that show what really happened inside a TypeScript AI agent run.

PlatformWebfreeglobal

agent-inspect turns an AI agent run's tool calls, LLM calls, logs, and failures into readable execution trees inspectable from the terminal, locally. It's built for TypeScript/Node.js developers using frameworks like LangChain, LangGraph, or Vercel AI who need to see what actually happened inside a run. It's aimed at developers debugging AI agent behavior rather than digging through raw logs.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of agent-inspect - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim agent-inspect to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether agent-inspect (or something else) actually fits.

Try a problem