I built a reader for the AI conversations I never re-read

Description and use

<p>There is about a million characters of AI conversation on this laptop. Seventeen sessions. Most of them were genuinely useful while they were happening: design arguments, debugging trails, decisions I would otherwise have forgotten by now.</p> <p>I never read any of it again.</p> <p>Storage was never the problem. Claude Code keeps a JSONL log, ChatGPT and Claude export zips of JSON. The data is mine, it is complete, it is backed up. It just isn't readable. One long column of messages, no chapters, no index, no way to get back to the paragraph where we settled on something.</p> <p>So I wrote

Problem

<p>There is about a million characters of AI conversation on this laptop. Seventeen sessions. Most of them were genuinely useful while they were happening: design arguments, debugging trails, decisions I would otherwise have forgotten by now.</p> <p>I never read any of it again.</p> <p>Storage was never the problem. Claude Code keeps a JSONL log, ChatGPT and Claude export zips of JSON. The data is mine, it is complete, it is backed up. It just isn't readable. One long column of messages, no chapters, no index, no way to get back to the paragraph where we settled on something.</p> <p>So I wrote

Outcome

<p>There is about a million characters of AI conversation on this laptop. Seventeen sessions. Most of them were genuinely useful while they were happening: design arguments, debugging trails, decisions I would otherwise have forgotten by now.</p> <p>I never read any of it again.</p> <p>Storage was never the problem. Claude Code keeps a JSONL log, ChatGPT and Claude export zips of JSON. The data is mine, it is complete, it is backed up. It just isn't readable. One long column of messages, no chapters, no index, no way to get back to the paragraph where we settled on something.</p> <p>So I wrote

Evidence

I built a reader for the AI conversations I never re-read

Source