this post was submitted on 08 Sep 2026
-73 points (13.9% liked)

Open Source

49043 readers
214 users here now

All about open source! Feel free to ask questions, and share news, and interesting stuff!

Useful Links

Rules

Related Communities

Community icon from opensource.org, but we are not affiliated with them.

founded 7 years ago
MODERATORS
 

πŸ’» I came across OpenClaude-Portable and I like the idea mostly because it reduces repeated setup.

It packages an AI coding agent into a self-contained folder and supports 9 providers, including Claude, OpenAI, Gemini, Ollama and LM Studio.

Settings, API keys and sessions stay inside the project directory.

Cloud providers still need internet, but with Ollama or another local provider the coding workflow can stay local once configured.

It supports Windows, Linux and macOS. πŸ’Ύ

To me, the interesting part is not "coding from a flash drive". It is being able to move the whole agent environment between machines.

Has anyone here tried doing this from a USB SSD in a real workflow?

top 11 comments
sorted by: hot top controversial new old
[–] aspmhzx@lem.cochrun.xyz 1 points 2 days ago

I went the other direction on this and made the runner something you host instead of making the agent portable. That's a project I'm working on, TaskHandoff (https://docs.thandoff.com/), so flagging it as self-promo up front.

The reasoning: with a portable folder the environment moves, but the machine you're sitting at still has to trust whatever the agent does there. With a self-hosted workbench you register your machines as workspaces once, then dispatch a task from the web UI and the session runs on the box you picked - local or remote. Sessions, credentials and task history stay on your side, and "moving between machines" becomes opening the UI from any of them rather than carrying the folder.

It doesn't replace the offline USB-stick case, that one still has no good answer. But for "same agent environment on three machines" the registered-workspace model is what actually stuck for me.

Out of curiosity - did you hit provider key sync issues when moving between machines? That was our other pain point, and it's part of why we kept credentials in one place.

[–] yxc999@lemmy.ml 20 points 1 week ago

how about no

[–] halm@leminal.space 10 points 1 week ago

Making slop easier, more convenient and even more commonplace? Nope.

[–] danielquinn@lemmy.ca 9 points 1 week ago

"Now you too can make it easier to pay big tech companies to sell your work back to you!". No thanks.

[–] borosilicate@lemmy.dbzer0.com 7 points 1 week ago* (last edited 1 week ago)

Let’s be real. You made this.

This project is ferociously ignorant.

At no point in your rambling, incoherent post were you even close to anything that could be considered a rational thought. Everyone in this thread is now dumber for having listened to it. I award you no points, and may God have mercy on your soul.

β€œNo installation required”. Scrolls down:

to install:

chmod +x start.sh
./start.sh

Just run this sketchy vibecoded executable and give it permissions. 😳

The only problem is people using LLMs and AIs.

[–] Dr_Vindaloo@lemmy.ml -4 points 1 week ago (3 children)

These comments are insane. I wonder if any of these people are actual software devs who have genuinely tried using a modern coding agent. Yes, there are issues with datacenters, investment bubble, circular financing, AI being used for discrimination and weaponry, etc. but those are problems of capitalism -- the tech itself is actually useful.

[–] LilyVess@lemmy.blahaj.zone 7 points 1 week ago (1 children)

It's useful. It's useful enough that justify the economy, climate, actual living places, etc 's cost?

I don't think so honestly.

[–] bountygiver@lemmy.ml 4 points 1 week ago

and dependency of a subscription to function

[–] Archr@lemmy.world 1 points 1 week ago* (last edited 1 week ago)

I have used an agent to try some test projects (this was about a year ago). I found that while the code did work for the most part, the agent overall produced code that was overly complex for what the initial brief asked of it. And that complexity made the code difficult to extend with even simple features.

I don't use one anymore because I figured that, for my job, maintainability is critical and I don't mind that the code takes me overall longer to write if it is well planned out and extendable.

Edit: I still would not use op's code since 1. It's not something I need, and 2. I don't trust it.

[–] Anarki_@lemmy.blahaj.zone 0 points 1 week ago

Actually useful in accelerating all this.