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.
The biggest thing is that Paseo's mobile app is out and pretty much has feature parity with its desktop app. I've been waiting on superset.sh's mobile app for a while, which is what made me look around and find Paseo. On desktop, they both get the job done and depend on whether you prefer a terminal-based or native chat experience.
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.
> Native support, Paseo ships a bundled adapter for the major agents (Claude Code, Codex, OpenCode, pi). Auto-discovered when the underlying CLI is installed, with mode metadata and voice support where applicable.
> ACP catalog, any agent speaking the Agent Client Protocol is supported through a generic adapter. Paseo ships a curated catalog of one-click installs (Cursor, Gemini, GitHub Copilot, Hermes, Kimi, Qwen Code, and 25+ more), and you can add any other ACP agent yourself.
> Either way, you install the underlying CLI. Paseo runs it.
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.
I really think that using something like Paseo (I use Ouijit[1] because I think it's actually a step ahead of where most of these multiplexers are) and nono[2] is basically the best coverage you can have, and really lets you go crazy with auto mode or permission skipping withiout having to worry about any security concerns.
A lot of people lean into the VMs but realistically it's not actually doing a lot of the security work that you need and leaves you wide open to prompt injection/exfiltration attaacks. The flexibility of a good nono setup (which is easy because they ship a nono skill that claude can consume) actually locks things down significantly better
It’s just a personal preference, to be honest, so I wouldn’t overengineer it yet. In my case, I run it in a VM behind Tailscale. The main reason is that I want it to be able to install or use whatever tools it needs without contaminating my main machine. It can expose anything I need over Tailscale. So for me, it’s basically just a cheap, throwaway machine.
I have a VM in which I run my general compute. In that VM I use incus linux container and run these tools as unauthorized user of the container. That should be reasonable security while having nice control for resources.
The split I've settled on: git worktrees for parallelism, containers only when I actually need isolation from the host.
Worktrees are cheap because they share the object store, so N agents each get their own working dir + branch without N full clones, and teardown is just `git worktree remove`. That solves the common case — two agents stomping each other's uncommitted files on the same repo. What it does NOT give you is isolation of the filesystem outside the repo, the network, or your secrets: a worktree agent can still read ~/.aws or curl anywhere.
So I only reach for a container/VM the moment an agent runs untrusted code or I care about blast radius — npm install on a sketchy dep, executing model-written shell, anything that could exfiltrate env vars. Rule of thumb: worktree for "don't let agents collide", container for "don't let an agent hurt the host". Most local setups only need the first, and people tend to reach for heavyweight sandboxing before they need it, then abandon it because it's painful.
A cheap middle ground that works locally: worktrees + a per-agent env file and a restricted PATH, so at least secrets aren't ambient without paying full container cost.
That is the value. You can run them remotely from your phone and set them up on a headless machine too. You’re not bound to your terminal.
My usual workflow is to still use the terminal for heavy work. But sometimes I just want to prompt from my phone and run a few tasks or do some planning. Then I can simply resume the session in the terminal later. It's the flexibility.
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.