DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to replay a finished agent run to review its subagents with Zoetrope

Scrub back through a completed session to see each agent and tool call in order.

Who it is forA developer or reviewer who needs to audit what an agent and its subagents did during a run that already finished.

The problemReading a long transcript to reconstruct which agent spawned which subagent and when takes time and is easy to get wrong.

The outcomeA replayed graph paced by the session's own timestamps, with the ability to scrub, pause and step between prompts to review each stage.

What you need first

  • Claude Code or Codex sessions already recorded on the machine (files under ~/.claude/projects/ or ~/.codex/sessions/)
  • Homebrew, a Rust toolchain for cargo install, or a prebuilt binary from the releases page
  • A terminal for the zoe TUI, or a browser for the hosted app

Steps

  1. Install Zoetrope with brew install furkankly/tap/zoetrope or use a prebuilt binary from the releases page.
  2. Run zoe with the path to any file of the finished session to replay it from the start.
  3. Press space to play or pause, and [ or ] to move between prompt eras.
  4. Drag the bar or scrub to a point of interest and click an agent for its prompt, reasoning and tool calls with timings.
  5. Press End or g to return to the live edge, then q to quit.

Prompt for your agent

Using the zoetrope repo (furkankly/zoetrope), replay the finished session at <session-file-path> with `zoe` and step through each prompt era. Expected output: a graph showing each subagent and its tool calls at the point it ran. Verify that the tool counts fall when you scrub backwards before reporting the review as complete.

Caveat. The replay reflects only what the transcript records, and Zoetrope skips unrecognized records rather than failing, so a gap in the graph may come from the file rather than the viewer.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page