Guides and reference for agentminutes.
Quickstart
Install agentminutes and parse your first transcript.
Use Cases
Why parse and compare agent transcripts across harnesses?
Installation
Homebrew, npm, PyPI, go install, and prebuilt binaries.
CLI
The convert, sessions, detect, stats, and drift commands.
Go Library
Whole-file parsing, streaming, transforms, and the ACP projection.
Session Discovery
Finding transcripts by cwd, session ID, and time window.
Subagents
Task summaries across subagent transcripts, and how each harness records delegation underneath.
The Schema
The normalized event schema and the guarantees behind it.
Comparing Token Counts
What token numbers mean per harness, which ones are comparable, and which comparisons are traps.
Harness Support
Supported harnesses, native formats, and validation coverage.
Design Notes
Loud failure, post-hoc parsing, streaming, and the explicit registry.
Example: Comparing Harnesses
Worked examples, from capture to side-by-sides of tool use, context, cost, failures, and delegation across harnesses.