I just launched alive-analysis an open-source workflow kit that runs inside Claude Code and Cursor.
Problem: you ask AI to analyze something, get a good answer, then a month later nobody can explain why we concluded what we did. Chat is gone and the logic isn t reproducible.
When you ask AI to analyze data, you get an answer—but a month later nobody can explain why. alive-analysis is an open-source workflow kit for Claude Code and Cursor. 5-step loop (Ask, Look, Investigate, Voice, Evolve), Git-tracked Markdown, checklists for confounders and Simpson's paradox. Quick and Full modes. Free. Install: clone repo, run install.sh, then /analysis-init and /analysis-new in the agent chat.
