feat(cli): show what the index holds, lead README with the payoff - #10
Merged
Conversation
`indexed N chunks from changed transcripts` is the first thing a new user sees, and
it says nothing about what they now have. The interesting facts are how far back the
memory reaches and that both engines feed it — and the second one is invisible in a
chunk total, even though a shared Claude + Codex history is the point of the tool.
your history: 1052 sessions spanning 168 days, 40,035 searchable fragments
Claude Code 372 · Codex 680
busiest: sidekey, trend_detection, glitch
README now opens on what the tool does for you rather than how it is built, and shows
that output plus a worked recall instead of describing one.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Зачем
indexed 2175 chunks from changed transcripts— первое, что видит человек после установки,и оно не говорит ему ничего. Сколько сессий? За какой период? Что там вообще лежит?
Главное — из счётчика чанков не видно, что историю кормят оба движка, хотя ровно это и
отличает инструмент от всех остальных.
Стало
Реальный вывод на живой истории, не выдуманный.
README
Открывается пользой, а не устройством: «Shared memory for Claude Code and Codex. Pick up work
from a month ago without re-explaining it». Дальше — этот же вывод и разыгранный пример
восстановления контекста, вместо описания того, как оно было бы.
Описание и топики репозитория обновлены отдельно: прежнее описание упоминало только Claude Code
и перечисляло механизмы (MCP tools + subagent + skill + hook) вместо того, ради чего это ставят.
Проверка
136 тестов зелёные, новый писался до кода. Сводка считается одним запросом на таблицу и не
трогает горячий путь поиска.
🤖 Generated with Claude Code