Hacker News: rbren

New comment by rbren in "Claude Opus 4.7 costs 20–30% more per session"

rbren — Fri, 17 Apr 2026 17:41:58 +0000

Good reminder to choose model-agnostic tooling!

New comment by rbren in "Components of a Coding Agent"

rbren — Sat, 04 Apr 2026 22:09:51 +0000

Strong article! I’ve been using the engine/car analogy for a while now.

If you want to play with the basic building blocks of coding agents, check out https://github.com/OpenHands/software-agent-sdk

New comment by rbren in "Cursor 3"

rbren — Thu, 02 Apr 2026 21:51:58 +0000

I still think every developer should be building their own IDE

https://github.com/rbren/personal-ai-devbox

New comment by rbren in "OpenYak – An open-source Cowork that runs any model and owns your filesystem"

rbren — Sun, 29 Mar 2026 17:00:18 +0000

It's probably just as hard to secure OpenClaw as this, but you'll find better tutorials for securing OpenClaw

New comment by rbren in "OpenYak – An open-source Cowork that runs any model and owns your filesystem"

rbren — Sun, 29 Mar 2026 16:59:42 +0000

The prompts contain e.g. a terminal UI, which gives you root access to the machine. If someone can access that UI and its backend, the can do whatever they want! So make sure to put it behind a firewall or basic auth or something else.

New comment by rbren in "OpenYak – An open-source Cowork that runs any model and owns your filesystem"

rbren — Sun, 29 Mar 2026 06:21:36 +0000

I still strongly believe every developer should be vibecoding their own cowork/openclaw/devin

Here are the prompts I use for my AI environment, though it's changed a bunch since the last snapshot

https://github.com/rbren/personal-ai-devbox

Show HN: My personal AI-powered dev workstation

rbren — Fri, 13 Mar 2026 17:26:40 +0000

Article URL: https://github.com/rbren/personal-ai-devbox

Comments URL: https://news.ycombinator.com/item?id=47367214

Points: 3

# Comments: 0

New comment by rbren in "Pi – A minimal terminal coding harness"

rbren — Wed, 25 Feb 2026 15:20:56 +0000

Funny, I just released my dev setup as “Open prompt”

https://github.com/rbren/personal-ai-devbox

New comment by rbren in "MiniMax M2.5 released: 80.2% in SWE-bench Verified"

rbren — Thu, 12 Feb 2026 19:04:07 +0000

A reasonably sized OSS model that's this good at coding is a HUGE step forward.

We've done some vibe checks on it with OpenHands and it indeed performs roughly as good as Sonnet 4.5.

OSS models are catching up

OpenHands Index of Coding Agent Performance

rbren — Thu, 29 Jan 2026 23:46:15 +0000

Article URL: https://index.openhands.dev

Comments URL: https://news.ycombinator.com/item?id=46818572

Points: 1

# Comments: 0

New comment by rbren in "I was banned from Claude for scaffolding a Claude.md file?"

rbren — Thu, 22 Jan 2026 20:46:30 +0000

This is why it's worth investing in a model-agnostic setup. Don't tie yourself into a single model provider!

OpenHands, Toad, and OpenCode are fully OSS and LLM-agnostic

New comment by rbren in "Agentic AI Foundation"

rbren — Wed, 10 Dec 2025 02:49:15 +0000

The OpenHands CLI has had some major improvements since v1: https://github.com/OpenHands/OpenHands

MIT license and model agnostic

I’d also keep a close eye on Toad which is launching this month:

https://willmcgugan.github.io/announcing-toad/

New comment by rbren in "Self-hosting my photos with Immich"

rbren — Sat, 06 Dec 2025 05:42:53 +0000

I use lychee. It’s been great. Uploads could be a bit rough a few versions back but they’ve been seamless for a while

New comment by rbren in "Agent design is still hard"

rbren — Sat, 22 Nov 2025 16:37:44 +0000

If you want to hack on an emerging agent SDK (specializing in software development), join us at https://github.com/OpenHands/software-agent-sdk

Show HN: OpenHands Software Agent SDK

rbren — Wed, 19 Nov 2025 19:04:37 +0000

Article URL: https://github.com/OpenHands/software-agent-sdk

Comments URL: https://news.ycombinator.com/item?id=45983642

Points: 2

# Comments: 0

New comment by rbren in "You should write an agent"

rbren — Fri, 07 Nov 2025 13:01:56 +0000

That's the idea! We have a confirmation_mode that can interrupt at any step in the process.

New comment by rbren in "You should write an agent"

rbren — Thu, 06 Nov 2025 23:34:09 +0000

Spoiler: it's not actually that easy. Compaction, security, sandboxing, planning, custom tools--all this is really hard to get right.

We're about to launch an SDK that gives devs all these building blocks, specifically oriented around software agents. Would love feedback if anyone wants to look: https://github.com/OpenHands/software-agent-sdk

New comment by rbren in "Open-Source Agentic AI"

rbren — Fri, 10 Oct 2025 04:08:27 +0000

If you're looking for open source agents, which can run locally, in Docker, or in the cloud, and which have a consistent track record of acing benchmark scores like SWE-bench, check out https://github.com/All-Hands-AI/OpenHands

We're about to release our Agent SDK (https://github.com/All-Hands-AI/agent-sdk/) which provides devs with all the nuts and bolts you need to define custom prompts, tools, security profiles, and multi-agent interfaces

New comment by rbren in "Bear is now source-available"

rbren — Mon, 01 Sep 2025 15:17:54 +0000

I’d like to see a “no jerks” license. It’d be MIT by default, but call out specific bad actors as being disallowed from using the software. That way your average corporate user wouldn’t need to consult a lawyer before adopting

New comment by rbren in "AI models need a virtual machine"

rbren — Sat, 30 Aug 2025 15:06:47 +0000

If you're interested in running agents (specifically for software dev) inside a sandbox, OpenHands [1] runs in Docker by default, and can run on Kubernetes or on a raw VM. It gets access to the standard tools (e.g. file ops, bash) as well as a web browser and a Jupyter notebook.

[1] https://github.com/All-Hands-AI/OpenHands