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

How to follow a running agent session as a live graph with Zoetrope

Watch the main agent, its subagents and their tool calls update live in your terminal.

Who it is forA developer who has started a Claude Code or Codex run in a project and wants to see which agents are working and what tools they are using right now.

The problemA long agent run is a stream of text in a transcript, which makes it hard to tell which subagent is busy, what it is stuck on, or how far the run has progressed.

The outcomeA live graph of the session with a card per agent showing status, current tool, tool count and output tokens, updating as the agent works.

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 cargo install zoetrope).
  2. Open a terminal in the project folder where the agent session is running.
  3. Run zoe to follow the current project's newest live session.
  4. Press f to let the camera follow the agent that just did something.
  5. Click an agent to open its detail panel, and press q to quit when finished.

Prompt for your agent

In the zoetrope repo (furkankly/zoetrope), install the zoe binary and run `zoe` from the project directory at <project-path> to follow its newest live session. Expected output: a live flow graph showing the main session and any subagents with their current tool. Verify that at least one agent card shows a status and tool count before reporting success.

Caveat. Zoetrope reads undocumented transcript formats that Claude Code and Codex can change without warning, so some records may render oddly after an update.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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