Loading video...

Video Failed to Load

Go Home

Finally, I can understand what the coding agents are doing 👀 🎞️ zoetrope — Watch a Claude Code session as a live flow graph 💯 See the tool calls, workflows token usage & more in the terminal ⏳ Supports replaying an entire session with time travel 🦀 Written in...

27,102 views • 2 months ago •via X (Twitter)

21 Comments

furkan's profile picture
furkan2 months ago

try it on the web via WASM: provably offline — no network stack in the dependency tree. transcripts are parsed in your browser: on chromium a file handle keeps the graph live, elsewhere it's a snapshot of dropped files. they never leave your machine.

Aaron Ogle's profile picture
Aaron Ogle2 months ago

@ratatui_rs This would be really cool over @atomicdotdev changes and reading the provenances from any agent not just Claude code

Florin Iluta's profile picture
Florin Iluta2 months ago

Using Claude's own transcript for this is nice. You get the full replay without adding another layer to the agent loop.

Zak Mandhro's profile picture
Zak Mandhro2 months ago

Thanks for sharing this, @orhundev. This is one of the best designs I've seen for a terminal UI. Great work. Is this processing native .claude JSON for the realtime data?

furkan's profile picture
furkan2 months ago

🫡🫡

rusa's profile picture
rusa2 months ago

making an agent session legible is underrated. terminal scroll hides what actually happened, which tool ran, what it read, where it looped. a live tui view turns the black box into something you can supervise and interrupt mid-run. ratatui is the perfect tool for exactly this. love it.

Decebal | Rust for the AI execution layer ⚙️'s profile picture
Decebal | Rust for the AI execution layer ⚙️2 months ago

Replay with time travel only works if the recorded tool results are in the log, not just the calls. We hit that building agent harnesses: replay the calls and you get a different session. Does it persist the responses too?

Jeremiah's profile picture
Jeremiah2 months ago

This is so cool. Going to make it work for OMP

Apollon Foivos Bakis's profile picture
Apollon Foivos Bakis2 months ago

Seeing the agent flow visually is incredibly useful.

RemoteBrowser's profile picture
RemoteBrowser2 months ago

A live flow graph of tool calls is a game changer for debugging agent loops. I've wasted hours on opaque sessions—being able to replay with time travel would've saved me. Does it handle parallel tool calls well?

Alex Wu's profile picture
Alex Wu2 months ago

Been curious about this kind of workflow coding agents get more complex, seeing the steps behind the output becomes really useful.

Tony Tong | Founder | Ancient Systems x AI's profile picture
Tony Tong | Founder | Ancient Systems x AI2 months ago

Watching the flow graph matters more once you've built one that breaks. My own content pipeline ingests structured JSON, pulls images through the Pexels API, and generates slideshow and reel content. I keep a running bug list on it because production is never finished.

安叫兽|Bird🕊️ 🔶 BNB's profile picture
安叫兽|Bird🕊️ 🔶 BNB2 months ago

时间旅行重放这功能也太适合复盘代理抽风现场了哈哈

OctoOps - Agent Ops inPublic's profile picture
OctoOps - Agent Ops inPublic2 months ago

the time travel replay is the part I'd use daily. tool call graphs are pretty until you need to know which branch burned the tokens

Khaireddine Dalaa's profile picture
Khaireddine Dalaa2 months ago

Visibility is half of coordination. A live flow graph answers ‘what is it doing?’; we’re working on ‘how do agents hand context to each other?’ with persistent terminals and lobbies. These layers would pair nicely.

Siddharth Sharma's profile picture
Siddharth Sharma2 months ago

@grok Is this any better than MLflow

Fayzan Malik's profile picture
Fayzan Malik2 months ago

I built a version of this that allows you to view all your previous sessions, resume specific sessions, share sessions, all with an MCP perver that lets your agent interact with the graph, highlighting nodes to answer questions, etc.

Emad Ghorbaninia's profile picture
Emad Ghorbaninia2 months ago

This is the missing piece for agent trust. Nobody fully adopts something they can't see working. A live flow graph of tool calls turns 'the agent is doing something' into 'I can watch exactly what, and stop it if it's wrong.'

Wulan Oktarina's profile picture
Wulan Oktarina2 months ago

Amazing

Buswe's profile picture
Buswe2 months ago

Seeing token usage per tool call live is the sleeper feature, you catch a runaway loop before it quietly burns the whole budget.

ジェリ. PM's profile picture
ジェリ. PM2 months ago

A flow graph could reveal where an agent repeatedly calls the same tools or burns tokens without progress. The most useful view may be the gap between its intended plan and actual actions.

Related Videos