Termi Protocol

Eric, I'm the exact target here, a solo dev running Claude Code all day, so "logs never showed me what they were actually doing" hits home :)Honest question: does the 3D actually change how you steer the agents, or is it delight on top? For one agent, watching a robot walk to its desk risks becoming visual noise after 8 hours. Where it'd be indispensable is the multi-agent case, does the room really encode state (this one holds a lock, this one's blocked) so you see a collision before it lands? That's the line between the product and a beautiful skin. Congrats on the launch! ;)

The visualization angle is interesting if it helps debug handoffs, not just make agents look fun. I'd be curious whether command/log events can be replayed later, because that would make it much more useful for reviewing failed runs.

Hello Eric. Congrats on the launch, very fun idea! How exactly can I control the agents if I just see them in 3D? These checkpoints are saved in local cache or inside the Termi server? Thanks let's connect :)!

Will watching them not burn more tokens? and be shit more expensive?

Exactly the answer I was hoping for — attaching to running sessions and keeping the render local is what makes it usable day to day. On the attach mechanism: does Termi tap the session by reading the PTY/terminal output, or hook into the agent process directly? And if I have two or three agents going at once (say Claude Code plus Codex), do they share one room or spawn separate ones?

Congrats on the launch. The local-first angle is the part I’d trust most here. For AI coding agents, visibility is useful only if it helps me make a decision: pause, approve, rewind, or compare what two agents changed.One small suggestion: make the “why this step happened” trail as important as the 3D view. Commands run, files touched, checkpoint reason, and approval history would turn this from a fun visualization into a review tool I could actually rely on.

The idea is really fun! Now I wonder - how deep it is connected with real activity of agents. Will it help to get visual signal that something is going wrong and can user control agents through those 3D models, or they are working only one side, just visualising the process?

That's interesting. Does it work with any agent that exposes terminal output, or only specific ones?

Giving agents a desk and a living room is delightfully absurd and weirdly useful at the same time - watching the process beats reading a wall of logs for spotting when an agent gets stuck in a loop. I live in Claude Code all day, so yes, I want to see my agent pacing around its office. Congrats on the launch!

Congrats with a launch!So we're not all confused here, it's just a fun project, you are not suggesting it as a serious workflow, right?

watching agents work in 3d is genuinely fun. i stared at agent logs for years and they never showed intent. does the view hint at why, not just what?

Very creative. I'm curious does visualizing the workflow actually help you catch bugs or inefficiencies that you'd normally miss in terminal logs?

the living room touch is genuinely clever, makes coding sessions feel less sterile than the usual terminal wall. nice execution on making agent work feel like something you'd actually want to watch.

Giving CLI agents a literal body in a 3D room is a clever way to make what Claude Code / Codex are actually doing legible instead of scrolling terminal logs. The practical thing I'd want to know: does Termi attach to my existing agent sessions (reading the terminal/process I already have running), or does it need to launch and wrap the agents itself? And does the visualization run fully local, or does it stream my file/command activity to a hosted backend to render the room?

the little office setup is weirdly charming, watching my agent pace around the room while it ran tests actually made debugging feel less painful. would love a way to peek at the full command output without losing the 3d view though