tablo
A tiny cat that watches your AI coding agents for you
Start new thread

tablo - A tiny cat that watches your AI coding agents for you

by•
You kick off an AI agent, switch tabs, and forget it's stuck or 90% through its context window. tablo fixes that, a tiny cat in your screen corner watching every Claude Code & Codex session: live context meters, tool approvals, and a nudge the second one needs you. Unlike usage dashboards, tablo tracks the conversation context filling up in real time, per session, across both tools — in a widget that stays out of your way. cozy by default. 🐱

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt 👋 I run a lot of Claude Code and Codex sessions at once, and I kept hitting the same annoying thing: I'd kick off an agent, switch tabs to do something else, and completely forget it was sitting there, stuck, or quietly burning through its context window until it auto-compacted and lost the thread. I wanted something that would just watch them for me without taking over my screen. So I built tablo, a tiny pixel cat that sits in the corner of your desktop and keeps an eye on every session. It shows a live context-window meter per session, surfaces tool approvals, and nudges you the second one needs you. Tap the cat or hit the shortcut to open a panel with everything at a glance; there's a dashboard too. A few things that made it fun to build: 1) the cat has moods: it sleeps when idle, starts running when agents are working, and gets alarmed when a session's near its limit. 2) it's a true desktop widget (Tauri), not a web dashboard and stays out of your way. 3) fully free and open source. It works best on macOS right now; Windows/Linux run the core but some bits are experimental. And a heads up: the "jump to session" feature (tap to focus the exact terminal/tmux pane) is marked experimental because focusing arbitrary terminals is genuinely a bit flaky across setups. Would love your feedback, and if you run coding agents, give the cat a try and tell me what's missing 🐾

I feel like coding agents are becoming something you supervise instead of actively use. I'm curious if you've thought about adding simple stats, like which agent spends the most time waiting for approvals or burns through context the fastest.

Maker

 
Thank you for the review !
Yes, I have thought about adding statistics while also keeping the application lightweight, it's primarily a widget so I have to make sure it does not eat up your machine's resources : )

love the cat mascot idea, super cozy vibe honestly. one thing i'd want though is a little sound or subtle notification when a session is about to hit the limit so i can wrap things up before it gets cut off mid task. right now i think it just nudges you right when it's already too late, like a few seconds before the cutoff. maybe a heads up at like 75% would be way more useful so you can actually plan the handoff

Maker

 
Thank you for the feedback !! Yes, these issues are already being tracked and will be resolved in the upcoming version : )

As someone who really likes cats, this is actually almost a must-have for me. Really fun little thing, I think it’s cool and somehow cozy too, it just gives the whole thing a different feel right away. Congrats on the launch!
Maker

 
Glad to hear that ! Keep looking forward to the amazing updates : )

A tiny cat watching my coding agents is genuinely delightful — and so useful. Congrats on the launch! 🚀

Maker

 
Isn't it ! : ) Thank you for the support !

This hits close to home. I run long Claude Code sessions for a data pipeline and losing track of a session mid-context-window is exactly the failure mode you're describing. The mood states (sleeping/running/alarmed) are a nice touch, way more glanceable than a numeric meter. Following to see how the Windows/Linux support shakes out.