alt Hacker NewsI went from TUI and tested several GUIs that can also support a "TUI" view.
After testing several options at the moment I'm using Orca IDE as my daily driver - effectively as a layer on top anthropic / openai
- Supports both anthropic and openai with subscriptions and can you swithc easily between those two + other LLms
- Its a bit hidden / non intuitive to setup but it does support running everything on remove host -> I run (95%) of my jobs on remote hosts that I can both access from my laptop + their native app via a wirguard vpn
- You can switch between chatview + TUI on the same conversation - very useful if you move e.g. from desktop session to mobile view.
- For repeating LLM tasks Orca also suports a kind of scheduler - but I prefer currently to have the agent set things up via chronjobs on the remote machine (not super happy with this ...)
Key reason I dont want to go fully ChatGPT/Claude is also I dont want to build a super strong dependency on those mega players and remain the ability to switch to other interefernce providers / models.
As LLM usage is already a core workflow in our company - a sudden unavailability of one or a massive price increase - makes it absolutely necessary to build out alternatives.
We all know the downsides of SAAS Lock in too well from the 2010s. In that sense Fool me once, fool me twice..
Replies
I built my own app Tomrade to do all my jobs in one place, it comes with an agentic built-in task management system like kanban board, and split-panel terminal. actually now I use Tomrade for everything except for code review, which I still use Orca. Having to say that Orca is doing a good job as ADE, so haven't had a plan to make another ADE inside Tomrade. https://tomrade.com
Yeah I tried going to GUIs aswell but ended up writing my own Terminal manager called switchboard. Since then I've tried a few others, like T3, which is pretty decent, but still keep coming back to Switchboard. It supports both Claude and Codex CLIs together with project grouping organization.
+1 on the Orca and remote machine. I've basically turned it into my own Claw machine. It does super well at letting me remote in across 3 computers and phone and hitting all the same sessions. I have one master session that is always kept alive as my main "agent", and spin out other full sessions from that.
It solves the crappy user experience of the CLI vs using an SSH terminal in VS code. (Easy copy pasting, everything formatted correctly, etc.) I created my own version of artifact hosting with a simple "mailbox" page on the box - every session can drop it's html reports off there nicely.
Completely agree on being able to flex out to different models. I'm using Claude Code as daily driver given the insane subsidies we are getting. But want something where I can switch easily onto the open weights, etc.
> Key reason I dont want to go fully ChatGPT/Claude is also I dont want to build a super strong dependency on those mega players and remain the ability to switch to other interefernce providers / models.
Pragmatically I agree with you, but I also believe that the landscape ahead is going to look so different that locking in to current tools won’t do anything to lock you in to near-future tools
Sadly Orca doesn't support chatview via WSL
Orca looks neat, but also super dangerous. It runs everything in yolo mode and actively fights staying in any sandbox you try to put it in.
TUI's might not have the best UI ever, but its much easier locking them down via something like nono.sh. I can sleep at night and not have to worry where my keys and .env files are being sent.