ahmadyan

why do you think the previous management team couldn't pull an Elon and fire 80% of the engineering staff themselves? why they needed an external leadership to take over and do it?

Part that i can't wrap my head around was at least in case of twitter, it was a hostile take over. In case of Vimeo, it didn't look hostile at all.

I believe this is using Virtualization.framework and not Containerization API from Tahoe, right?

Is there a limit on number of instances you can have per physical mac? i recall there was a hard limit of 2 because of EULA, unless Apple has changed it. (Cupertino really likes to sell you their Macs)

You mentioned "deleting the actual project, since the file sync is two-way", my solution (in agentastic.dev) was to fist copy the code with git-worktree, then share that with the container.

Very few people have the expertise to write efficient assembly code, yet everyone relies on compilers and assemblers to translate high-level code to byte-level machine code. I think same concept is true here.

Once coding agents become trivial, few people will know the detail of the programming language and make sure intent is correctly transformed to code, and the majority will focus on different objectives and take LLM programming for granted.

imho I think you benefit from better testing infra, as manual qa is your bottleneck. if you don't mind, what software is this?

it is your script, so you can do whatever you want; i just provide some env variables specific to the branch, e.g.

$AGENTASTIC_BRANCH $AGENTASTIC_BASE_BRANCH $AGENTASTIC_WORKTREE_PATH $AGENTASTIC_MAIN_REPO_PATH $AGENTASTIC_COMMIT $AGENTASTIC_REPO_NAME

if you give me some examples, i see i can also add that.

I had this ShowHN yesterday, which didn't grab much attention, so i'm using this opportunity as it seems relevant (it is a solution for running CC in parallel)

if you folks like to run parallel claude-code sessions, and like native terminal like Ghostty, i have a solution for using Git Worktree natively with Ghostty, it is called agentastic.dev, and it has a built-in Worktree/IDE/Diff/Codereview around Ghostty (macos only for now).

Would be happy to answer any questions

ShowHN post: https://news.ycombinator.com/item?id=46501758

ack

i run .agentastic/setup.sh script on every newly created worktrees (doc: https://www.agentastic.dev/docs/how-to/git-worktrees) and we set a few env variables in that script (e.g. current-worktree-dir, etc) so your stack should be supported https://docs.orbstack.dev/docker/

don't have shut-down yet, but i can add it as well (i.e. cleaning up the env upon deletion)

would a pair of setup.sh/shutdown.sh cover majority of your workflow? what else is needed?

not yet, just vanilla work-tree, so file isolation. I also poorly manage env isolation through running .agentastic/setup.sh script upon work-tree creation; which can setup .env files, etc.

I wasn't aware of branchbox, i was planning to integrate firecracker in the upcoming version. However Branchbox seems like a great option too.

Which set of container features / isolation matter to you more?

I hear you, and totally agree. I had the exact same problem. My goal is to simplify the process (but not too much) and reduce the mental demands of running agents, by automating at least work-tree management and code-review a bit at. So devs can focus on what matters more, higher-level planning, design and spec.

few reasons:

* Agents take a while to get the job done, so you give a prompt and you have to wait anywhere between 10mins-2hours or longer for it to finish. So it make sense to have parallel agents working on different features of the codebase. for example recently Boris, creator of Claude Code, posted about this setup where he is running 4-5 parallel agents in different tabs. https://x.com/bcherny/status/2007179833990885678 I personally have 30-40 agents running in parallel locally, and at the bottle-neck is the memory on my local machine.

* Even for the same prompt, the way i use the agent is run multiple agents with the same prompt, and review and pick the best output (Essentially pass@k for coding agents). This is specially useful for harder tasks, where I give the same prompt to both CC, Codex, Droid, and my own coding agent. Each model/scafold has its own distribution, and they work better when they are in distribution. So by sampling more, we increase the chance of success. (I know this is wasteful, but we currently live in the world of abundance cheap tokens; so put those $200 subs to good use)

So if we push this to the limit, i think we can improve the generation problem by shifting the complexity toward the verification. i.e. if you have 4-candidate solutions to your problem that all pass the the tests, how do you review and pick the best. This is where the code-review comes in.

My issue with most of them is the xterm.js, which can't handle when the terminals get large/too big, Even Conductor (great app, i love conductor and the team behind it) had to drop their "big-terminal" mode. i'm hacking a native solution for this which i personally like by hacking Ghostty+SwiftTerm.

They need to compile the model for their chips. Standard transformers are easier, so GPT-OSS, Qwen, GLM, etc if there is demand, they will deploy it.

Nemotron on the other hand is a hybrid (Transformer + Mamba-2) so it will be more challenging to compile it on Cerebras/Groq chips.

(Me thinks Nvidia is purposefully picking architecture+FP4 that is easy to ship on Nvidia chips, but harder for TPU or Cerebras/Groq to deploy)

Congrats on the launch, Nia looks great.

of course,

cathedral = sandbox env in the provider's cloud, so [codex](https://chatgpt.com/codex) uses this model. Their codex-cli product is the Bazaar model, where you run in your computer, in your own environment.

Claude Code, on the other hand, doesn't have the cloud-based sandboxing product, you have to run in on your computer, so the bazaar model. You can also run in in a way that anthropic never envisioned (e.g. give it control to your house). Curser also follows the same model, albeit they have been trying to get into the cathedral model by using the background agent (as someone also pointed out below). Presumably not to lose the market share to codex/jules/etc.

Codex/Jules are taking a very different approach than CC/Curser,

There used to be this thesis in software of [Cathedral vs Bazaar](https://en.wikipedia.org/wiki/The_Cathedral_and_the_Bazaar), the modern version of it is you either 1) build your own cathedral, and you bring the user to your house. It is a more controlled environment, deployment is easier, but also the upside is more limited and also shows the model can't perform out-of-distribution. OpenAI has taken this approach for all of its agentic offering, whether ChatGPT Agent or Codex.

2) the alternative is Bazaar, where you bring the agent to the user, and let it interact with 1000 different apps/things/variables in their environment. It is 100x more difficult to pull this off, and you need better model that are more adaptable. But payoff is higher. The issues that you raised (env setup/config/etc) are temporary and fixable.

Why?

For $200plan, it has 40M token cap per day, so assuming the API pricing, the max usage per day is $12/day or 360 per month. (Assuming user max-out usage every day or doesn't hit the 1000message limit first)

relatively standard subscription pricing vs API pricing, i believe they are making money from this and counting on people compare this to Claude Code, which is a much more generous offer.

Congrats on Qwen3 launch, also ty for the exploration tier. Makes our life a lot easier.

Any plan/ETA on launching it's big-brother (Qwen3-code)?