VibeTrace — Session replay board for AI coding agents

Turn scattered coding-agent sessions into searchable team memory

Problem

Teams run Claude Code, Codex and Copilot CLI side by side, infer task state from terminal byte activity, and can't reconstruct which step changed what or why. When people or agents change, context is lost and reviews mean digging through terminal history.

Solution

A local-first board that collects session events via each agent's lifecycle hooks, rebuilds timelines by task, file and decision point, and supports search, export and PR comment attachments. It doesn't write code; it visualizes which agent did what and on what grounds.

Users

Engineering teams using multiple coding agents, tech leads doing reviews, freelance developers who must explain changes to clients.

MVP

Hook-based event reporting for Claude Code and Codex; timelines aggregated by task and file; keyword search and session export; generated change summaries to paste into PRs; local storage with zero upload.

Revenue

Free individual tier; per-seat team subscription with shared timelines, permissions and export to Confluence/Notion; self-hosted enterprise tier.

Why now

Coding agents are spreading fast and now support hooks, making event data collectable for the first time. Teams already mix multiple agents, but the memory and audit layer is still missing.