back
92 comments
I prefer Paseo https://github.com/getpaseo/paseo, mainly because I have specific preferences for different harness + model combinations. For example, I like using ChatGPT models via pi, and GLM via Claude Code.

If you’re happy with OpenCode as the harness, OpenChamber is great. But if you prefer using different harnesses under the hood, Paseo is a better fit.

I installed it on my homelab and can access the same sessions from my MacBook or iPhone at any time. Been really nice to use so far.

+1 for Paseo. Switched over to it a few weeks ago from conductor.build then superset.sh. The mobile app plus Hetzner VPS has been really enjoyable in terms of just firing off random tasks and not being stuck at my desk.
As someone who uses both Claude Code and Codex, having a unified interface while still being able to use their respective harnesses is a godsend. I've tried a lot of alternatives, and nothing even remotely comes close to the level of polish this one has. The session sync is buttery smooth as well, it's even better than Claude Code mobile I would say. Thanks so much for the recommendation.
Another +1 for paseo. I've been dabbling with all these tools and I love how they are progressing. But im constantly patching and filing issues on them. Only paseo and openchamber handle mobile terminal scolling well. Paseo has been the most feature complete one with claude and open code support with a top notch mobile experience.
this looks prettttttty slick i might dive in later.

are people using these things but isolating agents to some sort of containerization individually or do you have like one big dev env ? probably time i get around to sorting a better dev container strategy just to isolate agents here but trying to think of the best way to set this up locally.

what is the goal of these tools, having a hard timeunderstanding the value vs just running them on terminal
Not only is it good - but the maintainer is active and really nice, helped me fix two bugs straight off the bat!
+1 for paseo. Switched yesterday and it’s a dream how flexible and clean it is.
Had to scroll all the way to the bottom to see that its a wrapper for OpenCode.

This actual functionality should be more explicitly stated, and should be described much sooner IMO.

on the scroll note, the top background had a seizure while i was scrolling down
I'm using Orca recently for both coding and as a terminal and like it a lot, seems this is very similar, just tied to a single harness?
Orca is my main ADE too, but I haven't found any other users!

What do you when done with a work tree? Just delete? I wish there was a middle ground of hiding it from the main panel, but keeping it for a week or so just in case I need to refer to something in the transcript...

Huge fan of Orca. Been using it for a month. Plan to setup a proper remote env this week.
I wonder what JetBrains is doing. They had such a strong lead, but with the rise of AI, they seem to be heading down the same path as Stack Overflow.
I've been paying JetBrains in a personal capacity for about 15 years. Almost from the first year of my professional career. I didn't renew this year. I feel so sad and disheartened that a company that produced such brilliant tools have completely lost the plot on AI. They had started work on Fleet, a lightweight VSCode like IDE, before LLMs became big, but abandoned the effort without seeing it through. It could've been a great agentic IDE (all I want is whole file+project view for every conversation, instead of just diff so I can have a better perspective of the codebase). Instead they built multiple confusing tools (might be internal org structure and competition leaking out), and took far too long to adopt SOTA CLI coding agents, and kept charging for it as a separate subscription. I wish they do a whole company rethink on agentic development, but it is going to be tough because the existing enterprise licenses will continue to be the main revenue driver for a few more years, until it all dries up all at once.
Same thing. I've been using JetBrains IDEs for 25 years, and by now the keyboard shortcuts are hardwired into my fingers.

They fumbled the initial rollout with the way they gate-kept the agents behind their own subscription. I used Claude through its API pricing for a while, and the UI experience with the sidebar chat was so much better than the Claude CLI.

I could see the thought stream, click on artifacts, view diffs, etc. But it burned through tokens way too quickly, so I downgraded to the CLI agent.

At least I can use IDEA's inspections through the MCP server. It enables the agent to use the IDEA's index for navigation (finding usages, locating symbols, etc.)

They have the Air and it's quite nic for agentic coding.
I use IntelliJ at my current gig—and the CoPilot plugin for AI, because it’s what I have access to—and it has become ClaudeCode-esque of late: sub-agents, skills, tool-calling, hooks…and continues to improve. It’s unfortunate how the AI-in-a-sidebar UI kind of hides how sophisticated it has grown, but it’s a glass of ice water in hell in an environment where you can’t easily procure what you want.
I let my Pycharm sub lapse since I switched to VSCode. Its lighter and better at some static analysis.
Seems like another clone of Conductor, though this one has a serious amount of feature creep (supporting so many platforms will add a ton of extra complexity), and on OpenCode SDK only.

As a simpler desktop-only multi-platform option, I can highly recommend Termic (https://github.com/simion/termic). It just runs existing TUI coding agents (so Codex, Claude Code, OpenCode, etc) and manages them in sandboxed git worktrees. You get a real PTY to manage agent in, lets you see when one is working or has paused, plus a terminal, "changed git files", even in-line-code comments you can feed back to the agent. It's a good design, works well, the main dev is working very quickly on improvements, and they're responsive to issues and PRs.

This field is super crowded, but we are still working on our own ADE called Podium and think we have something unique.

Features we are proud of are one click onboarding of new VPSs into the agent fleet. Agent orchestration across different machines and harnesses. As an example, a Codex coordinator on one machine can run a Grok implementer subagent on another machine and they can talk to each other.

It's not really ready for public consumption yet, but it's been our exclusive daily driver for the past month. We'd be happy for people to test drive it and provide feeback regardless: https://github.com/madeinorbit/podium

It's funny / ironic how the whole agentic development boom has taken off in terminal environments, but now the orchestration / IDE layer seems to be all Electron / GUI apps.

Any suggestions for terminal UI versions of something like this?

It's nice but I get such memory leaks that I have to reboot my bacbook after a few hours of using it. Sticking to opencode gui for now.
Looks nice.

I have a number of these pieces in a binary I drop first thing on every agent computer: https://github.com/housecat-inc/scratch

Chat to code with an inspector to point at specific DOM sections, review diffs on the box, hand off to mobile, etc.

Makes me wonder where all this will end up. Or DIY win with hyper-personalized tools? Will one vendor become the center of gravity similar to VSCode in previous generation? Will there be a cottage industry of more opinionated tools?

This looks pretty awesome, like almost exactly what I've been hoping for. Is it possible to run the sessions on a remote server to keep tasks running? I mostly work from my laptop and it's nice to fire off tasks to a remote server (mostly been Cursor Cloud Agents lately) and close my laptop, maybe check in from the app later.
Somehow reminds me of JetBrain's new Air [1] platform (still in beta I think) - make multiple agents working, monitoring, basic code and diff viewing.

[1] https://air.dev/

Not surprised at all but there seems to be tons of these kinds of tools and I'm having a hard time picking one. Is there a nice list somewhere? I guess I can ask chatgpt...

Honestly right now I do a lot of development from my phone - I don't have the time to pull out my laptop very much. Right now I use hermes agent and just chat with it on Slack. But sometimes I wish I had easier access to more advanced features, and Slack isn't the best UI for this stuff. So I want to use something like this but am having analysis paralysis.

> development environment

First screenshot is of a phone.

Yeah I’m never installing a coding agent on my phone.

I really enjoy the sidebar style for organising work, I’m not sure why the OpenCode desktop app moved to browser-like tabs (horizontal ones, though tbh my browsers now have vertical ones ehh).
Why use this over T3 Code?
Over 50 npm dependencies (dev and non-dev). Is this really how things are developed in 2026? After all what's happening (cyber security), is any developer out there running this kind of software just like that in their main machines without any concerns?
This appears to be somewhat like Paseo, specialised for OpenCode under the hood?
Paid an artist for the artwork rather than have it AI generated peaked my interest.

Makes it feel like actual effort went into this. :)

Try codecast for a better version of this that works across all agent harnesses in one unified way.
OpenEverything
Sticky header with no background seems a bit awkward on mobile. The text overlaps.
I have been using Opencode desktop, going to try out these other tools too
Oh, I love the idea of a changes walkthrough. Maybe I'm old fashioned but I still look through all the code and prose that gets committed. In Orca, it took me about half an hour to even find the diff view (hidden behind a panel, activated on the top right)

I've said it before and I'll keep on saying it: the churn in new dev interfaces it's super exciting. Can't wait to see what next week brings.

"Desktop app", aka packaged Web.
This looks neat. How is this different from Jetbrains Air?
Since this page is clearly made with AI, someone deliberately prompted to add scroll hijacking for some reason, despite it being known to be bad UX.
is agent orchestration somewhere in your backlog?
Is saying "XXX: An Agentic Development Environment" already sufficient to get to the front page of HN? I guess no differentiation is even required in this category, huh?
Looks interesting, might try it out. I have to ask, did you really need to hijack my scroll behaviour?
From now on I swear if I launch a new product I will call it ClosedXXX
This looks very nice and well done. Good job! Okay, I'm going to have a tongue-in-cheek rant now.

OpenChamber, OpenAI, Open WebUI, OpenDoor, Open weights, OpenTable, OpenClaw, Open This, Open That. We're increasingly diluting the meaning of the term, and "open source" more broadly, that we're at the point of OpenFatigue being a real concern here.