Siddhant-K-code/agent-trace

strace for AI agents. Capture and replay every tool call, prompt, and response from Claude Code, Cursor, or any MCP client

34
/ 100
Emerging

This tool helps software developers and engineers understand exactly what their AI coding agents are doing behind the scenes. It captures a complete record of every action the agent takes, including tool calls, file operations, prompts, and responses. Developers can then replay these sessions to debug issues, audit agent behavior, and understand why certain decisions were made.

Use this if you need deep visibility into the entire lifecycle of your AI coding agent's actions and decisions, beyond just the LLM calls.

Not ideal if you only need to trace the LLM prompts and responses without detailed insights into the agent's tool use or internal operations.

AI-agent-development software-debugging developer-tools code-generation observability
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

MIT

Last pushed

Mar 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Siddhant-K-code/agent-trace"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.