35 comments

[ 2.7 ms ] story [ 81.7 ms ] thread
I'm really looking forward to trying this out over Christmas break. Textualize is awesome for building Python console apps.
Me too. I am on a mobile device but I put the article link on my TODO list.
This looks really cool. I wonder if they support vi keybinds
First thing I thought of, too. If not, I hope it’s planned. I’m all in on TUI tools, and vi keybinds are a necessary part of that for me.
Not planned for now I believe, you could try making a new Discussion for it.
Hi. Will McGugan here. I built Toad. Ask me anything.
Sorry, not a question, just wanted to say congrats on putting this together. I am so the target market for a nice terminal interface. I can’t wait to try this out!
Very interesting project! I have 2 questions:

1. How has it been working with ACP? Is it anywhere near feature parity with Claude code’s native interface?

2. I see your repo is written in Python which is interesting to me for a responsive TUI. Is it snappy and performant and if so what gave you done to make it feel native? And why did you choose Python?

Cool idea but why python?! Rust please and I’m all ears.
The author is also the creator of the textual Python library for creating TUIs. The performance benefits of Rust don't seem very useful in a tool where you spend a few seconds typing in a prompt and then 90% of your time is spent waiting. As long as the UI is responsive when typing there wouldn't be much of a difference.
The creator of Toad, made a TUI framework in Python (Textual). What is so special about Rust, aside from it being blazingly fast and compiled, that you want from it?
Toad looks really nice, I will definitely try it out. I have some ACP questions if you don't mind.

First, from my reading of the ACP doc, one thing that seems pretty janky is if the ACP client wants to expose a tool to the agent, e.g. if Toad wanted to add the ability for the agent to display pretty diffs. In the doc they recommend stdio to the ACP server, then stdio to an MCP server, and then some out of band network request back to the ACP client. Have you thought about this, or found a better solution working on Toad?

Similarly, it would be useful to be able to expose a tool which runs a subagent using ACP using a different agent, e.g. if I'm using Claude for coding but I'd like to invoke codex for code review. Have you thought about doing anything like this? Is it feasible over the protocol?

Hi Will,

I was about to try opencode after using claude code for quite a while.

I think understand the fundamental difference in how they work (acp against existing agentic loops with toad vs a single agentic loop for all models with opencode) but I’m curious why we might want toad over something like opencode, which lets me use any model under the sun.

I suppose toad gets to use the highly specialized agentic loops for each cli. And has a nicer (? opencode is pretty slick from my brief usage…).

Curious to hear about why you chose to built this way and what advantages you see.

I'm using ollama with local LLM for completion (tabby-ml) and Open WebUI for chat. What will be the goto local ACP server working with ollama ?

Ideally working with toad to experiment with it.

fast-agent has ACP support and works well with ollama. Once installed you can just use `toad acp "fast-agent-acp --model generic.<ollama-model>"`.
Hey Will, just wanted to say this looks pretty damn spectacular. No notes. :)
This looks great! Looking forward to trying it out. I recently tried moving to OpenCode but it didn’t quite scratch the itch UX wise.
I see what you did what that intro and I approve :)
This is absolutely awesome but the little jokey captions that Claude did (Discombobulating... Laminating...) all that stuff, they were a little annoying but cute enough, but whatever is running this one (I did not murder him... I thought I was special....) they are genuinely offputtingly bad. This great app doesn't need clunky humour front and centre, I'm not sure if it's Claude or toad but it seems markedly worse than Claude used to be.
I already used Toad to run a conversion task I've been procastinating on.

It worked perfectly and looked splendid doing so.

Excited to dig in further.

toad is next level in many ways
Very excited to see this come out - though coding agents are impressive their UIs are a bit of a mixed bag.

Textual offers incredibly impressive terminal experiences so I'm very much looking forward to this.

I wonder how much agentic magic it'll be able to include though - Claude Code often seems like a lot of its intelligence comes from the scaffolding, not just the LLM. I'm excited to see!

It would be a matrushka to run Toad in a Zed terminal.
The name Toad gave me a flashback to Tool for Oracle Application Development, an IDE and debugger for SQL and pl/sql back in the 1990s.
I’m not a big fan of the name Toad, but the Textual framework is fantastic. I’ve been using it for years in a small project and it’s just a wonderful tool - it makes it really easy to get a super fast little UI for scripts.
I strongly resonate with the problem statement, but this implementation was very far off the mark for me. Every interaction feels bad.

I fired it up, and the first thing I notice is that the arrow keys don't work. I can't select Claude Code. Oh, apparently it's in a different control, so I have to press Tab, and then the arrow keys work. Wow, this list of buttons has a slow scrolling animation when navigating it. Can I turn that off? Press enter on Claude, now I'm in a tiny modal window. Press enter, because I want to do the obvious thing, but apparently the obvious thing is "show in launcher", so the background of the modal is weirdly changing while a tiny single character inside the button is indicating that this is the part I'm supposed to be focusing on. No, I want to do the obvious thing of running Claude code. You could easily fit the 4 actions of this form on my screen, but by choosing to use a tiny modal window you're now forcing yourself to use another modal drop-down control to choose the action and a separate "yes actually do it" button, so the OBVIOUS ACTION of RUN THIS AGENT requires pressing tab, enter, down, down, down, enter, tab, enter. Great. Now I'm at a chat interface with an error screen, because it isn't installed. Quit the program, restart, enter, tab, enter, down, down, enter, tab, enter to install. It shows a successful run of the "ACP adapter" for claude. Shift-tab, enter, down, enter, tab, enter. Now I'm back at exactly the same error screen because apparently the install didn't work. Now, I know that you need to be running "npx @zed-industries/claude-code-acp", so I check the docs and apparently I can "toad run COMMAND". But it doesn't work for multi-word commands. And my trial with toad comes to an end.

So I can't test it for anything actually useful right now, but I'll add this to my list of projects to watch. Hopefully, being a UX-focused project, the creator actually focuses on the UX and fixes some of these silly decisions.

This looks fantastic!

Check out vibecommander - it’s a young tool in this space with a different take that wraps around CLI coding assistants with IDE-style file and git panels that compliment the experience by letting the human do the code review part of the task seamlessly.

Will add Toad support ASAP, I’m sure they’ll be great together.

https://github.com/AvitalTamir/vibecommander

Long time `rich` and `textual` user here, just wanted to say thanks :-)
Congrats and thank you for making Rich and Textual
(comment deleted)
I've long been integrating terminals with GUIs and wanting more of this sort of stuff.

Reading the article I felt like the "sickos: yes!" meme.