MIDREAL
Menu

Show HN: OpenComputer – an open source alternative to Devin

https://github.com/diggerhq/opencomputer (github.com) REAL

120 points | 36h ago | Discuss on Hacker News | Back to Radar

Comments

taudas 36h ago on HN
New product name please, your current name tells us nothing and is already taken. But I am still going to try it :)
iacguy (author) 36h ago on HN
Curious which other product you're referring to? But valid will take a look on the naming conflict.

And yes please give it a shot and let us know what you think!

nasso_dev 33h ago on HN
personally i think of OpenComputers, a minecraft mod
rl3 35h ago on HN
>... your current name tells us nothing ...

A little harsh, but at least it's leagues ahead of Devin.

iacguy (author) 28h ago on HN
fwiw - Devin is a great name and we have a lot of respect for what they’ve built!
igorzij 35h ago on HN
thanks!! we'll seriously consider, fr
namanyayg 35h ago on HN
Open source is amazing! Any insights how you've made something so cheap and fast? Are the margins charged by Devin really this insane?
igorzij 35h ago on HN
thanks!!

we've invested heavily into infra one of the non-trivial things we did there is 2 levels of isolation instead of one there are VMs with fast NVMe disks and then inside VMs lighter rootless podman sandboxes - and each organisation gets a fleet of N VMs dedicated, N>=1

this way the VMs serve as a "soft" concurrency limit and all sessions are still isolated, guaranteed to run on your VM, and start fast

Atotalnoob 34h ago on HN
Devin charges a premium markup and has switched their default model to a very cheap, low quality model.

At my organization, all of the skilled engineers use Claude Code and the bad ones use Devin cause it’s “easier”.

It shows in the code thats written

jkelleyrtp 30h ago on HN
> Devin charges a premium markup and has switched their default model to a very cheap, low quality model.

I work at Cognition. This is not true. The picker currently has:

- Normal: Balances cost and intelligence with models like Opus 5.5 and GPT-6.2 Sol

- Ultra: Highest intelligence available with Fable 5.2 and GPT-6.2 Astra

- Lite: Fast lightweight models

- Fusion: Multi-model harness that pairs frontier models like Opus 5.5, Fable 5.2, and GPT-6.2 Astra with a cost efficient sidekick for up to 30% cost savings

And then you can select any of the "preview" models like SWE-2, GPT 6.2, Gemini 4 Neon, Fable 5.2, etc.

The built-in modes are basically just "best model at xyz on cost curve" and then we have individual models people can select.

dabit3 30h ago on HN
Hi, I work with the Devin team at Cognition:

"Premium markup." If you go past the usage included in a paid plan, extra usage is billed at API pricing. In September Devin also got 30–40% cheaper in Fusion and Normal mode and 15–20% cheaper in Ultra while quality held or improved at every mode.

"Cheap, low-quality default model." Devin isn't tied to one model. Our normal router uses Opus 5.5 at the moment (or GPT-6.2 Sol high on GPT plan), and Ultra uses Fable 5.2 (or GPT-6.2 Astra high on GPT plan), only when someone chooses the light mode specifically are they routed to SWE-2 which is actually a great model trained specifically for software engineering that benches really well and developers really love (and SWE-2 inference / usage is currently free).

"Only the bad engineers use it." Our users include engineers from Nvidia, Exa, Modal, OpenRouter, Mercor, Ramp, and hundreds of other companies with a high bar for engineering talent, and the best ones seem to really love and appreciate the quality and shipping velocity they get with Devin.

I encourage anyone reading this to consider asking someone they know who's used Devin within the past few months for their opinion.

cadamsdotcom 27h ago on HN
Sorry but this comes off as sycophantic and thus inauthentic.

If you invested in the company, or are affiliated somehow, consider disclosing..

sausagefeet 19h ago on HN
Weird that the comment is from someone who works at a GTM contracting company...
lawnchair 19h ago on HN
LOL this is clearly a fake comment. What a joke.
sleepytimetea 35h ago on HN
Don't have Slack, will it work with Discord ?
motatoes 35h ago on HN
hey! founder here. We have a web ui and a cli as alternatives, you can also integrate the cli with local coding agents or things like openbot. Discord can be on the roadmap! Hope you can try it and file feature request for us
Vaudtje 18h ago on HN
T3 code remote integration?
igorzij 34h ago on HN
not yet but on the roadmap!
andyjtyler 35h ago on HN
is the whole thign open source? like can i spin it up in my own infra or just the harnesss code?
iacguy (author) 34h ago on HN
Yes - the repo is Apache 2.0. For the harness specifically, you byo Claude Code/ Codex.

You need one VM in your cloud plus Cloudflare Workers (the runtime of which is also open source as workerd) for Slack events.

hasbot 33h ago on HN
Probably best to explain what this is directly without expecting people to know what Devin is.
izalutski 32h ago on HN
this makes Devin an OpenComputer alternative!

right? right..?

nitroedge 30h ago on HN
Have you heard of Windsurf?
esperent 26h ago on HN
About a year ago I think, yes. But I've heard of at least 100 other agentic tools in that time and I don't recall what most of them do. What's windsurf?
NetOpWibby 25h ago on HN
Not sure why you're being downvoted, you're right. I didn't know what Devin was. https://news.ycombinator.com/item?id=50586844
SilentM68 32h ago on HN
I see the word self-hosted but don't see any mention of Ollama or dedicated home self-hosting scenario.

What if somebody wants to just self-host on a home pc, say using Ollama to serve the models? Does OC work w/ Ollama directly, providing "its own agent capabilities" rather than relying on other agents e.g. ClaudeCode, Codex, OpenCode, etc?

Will any of the above be supported in the future?

izalutski 32h ago on HN
we're planning to give at-home setups more attention at some point! for now meaning self hosting as in "in my team's cloud acct"
swyx 31h ago on HN
how do you compare your approach to OpenHands (fka OpenDevin)? (https://ai.engineer/talks/iH_wV8BbS24)
iacguy (author) 31h ago on HN
Big fans of OpenHands.

The main difference from our pov is that OpenHands is an agent with its own harness. We’re unopinionated on the harness and more focused on the infrastructure it runs in. In fact we started as one of the first “persistent” sandbox providers [1]. OpenComputer runs the user’s Claude Code or Codex (you pick per thread), and you can bring your own ChatGPT/Codex subscription.

Our focus is predominantly on building high perf specialised infra for cloud coding agents. eg: each Slack thread gets its own rootless Podman container, with state written to local disk and then persisted to a git backed store. That’s why it feels like Claude Code on your laptop: in our benchmark it opened PRs 3.3x faster than Devin, with first push in 24s vs a 62s average across the 4 most popular cloud agents [2]. It's also cheaper at at scale, we've found, than an ephemeral sandbox per session [3].

[1] https://x.com/utpalnadiger/status/2047436177016537251 [2] https://opencomputer.dev/blog/cloud-agents-as-fast-as-local/ [3] https://opencomputer.dev/blog/opencomputer-open-source-devin...

swyx 18h ago on HN
ahh ok good reply. in that case the "open source Devin" is underselling it. will give this a go.
NetOpWibby 25h ago on HN
For people (like me) who don't know WTF Devin is: https://devin.ai
hobo123 24h ago on HN
the editor formerly known as Windsurf.
htgb 24h ago on HN
I didn't realize they both came from the same company. Apparently Windsurf was renamed Devin Desktop.

What I associate Devin with, and what this seemingly competes with, is the cloud hosted version. The UI and harness as well as runners are hosted, and multiple people can prompt in the same session.

izalutski 21h ago on HN
yes, the cloud piece is the main part - it has multiple clients, web, cli, API so you can build your own. desktop coming at some point too
Halto 24h ago on HN
what actions does agent do without any check of system and how do you control it
nzjrs 23h ago on HN
I learnt more by visiting the Devlin Hompage and learning what it was...

Comments are loaded live from Hacker News and are not stored by Mid or Real.