Agent Debugging Python Packages

claude-tap

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

valanistack

AI agents fail like junior teammates, looping on bad ideas, ignoring feedback, and escalating commitment. vstack ports 34 of the most-cited organizational-behavior frameworks so you can diagnose your agents the same way you'd diagnose your team.

agentdelta

Diff and regression-detect LLM agent execution traces

browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

continua-sdk

Self-hosted durable execution engine with built-in observability for AI agent runs