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

agent-trace

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

Why

A coding agent rewrites 20 files in a background session. You get a pull request. You do not get the story. Which files did it read first? Why did it call the same tool three times? What failed before it found the fix?

Most tools trace LLM calls. That is one layer. The gap is everything around it: tool calls, file operations, decision points, error recovery, the actual commands the agent ran. agent-strace captures the full session and lets you replay it later. Export to Datadog, Honeycomb, New Relic, or Splunk when you need production observability.

Install

# With uv (recommended)
uv tool install agent-strace

# Or with pip
pip install agent-strace

# Or run without installing
uvx agent-strace replay

Zero dependencies. Python 3.10+ standard library only.

Quick start

Option 1: Claude Code hooks (full session capture)

Captures everything: user prompts, assistant responses, and every tool call (Bash, Edit, Write, Read, Agent, Grep, Glob, WebFetch, WebSearch, all MCP tools).

agent-strace setup        # prints hooks config JSON
agent-strace setup --global  # for all projects

Add the output to .cursor/settings.json. Or paste it manually:

{
  "hooks": {
    "UserPromptSubmit": [