claude-tap exposes live traces for Claude Code and Codex-style agents
dotey · x · 2026-07-24
claude-tap is positioned as a local observability and trace viewer for AI coding agents like Claude Code and Codex.
It lets you inspect a real agent run in detail, including:
- system prompt and conversation history
- tool schemas, tool calls, and tool results
- streaming responses
- token usage
- structured diffs between adjacent requests
The post argues that the fastest way to learn Claude Code / Codex harness engineering is to compare source code with real traces, so you can understand how context is assembled, tools are registered, state is passed across turns, and requests evolve over time.
More from coding & agent
- Inspired by OpenAI's 10,000-agent run, dev open-sources a crowdsourced agent problem-solving platform — Benjaminsen · 2026-09-11
- Lucid: open-source Mac app keeps your laptop awake only while AI agents run — Pitiful_Hedgehog_600 · 2026-09-11
- banteg's snail project crowdsources AI agents to finish matching Snail Mail's 20 remaining functions — banteg · 2026-09-11
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11