[HN Gopher] Show HN: Open-source alternative to ChatGPT Agents f...
___________________________________________________________________
Show HN: Open-source alternative to ChatGPT Agents for browsing
Hey HN, We are Winston, Edward, and James, and we built Meka
Agent, an open-source framework that lets vision-based LLMs execute
tasks directly on a computer, just like a person would. Backstory:
In the last few months, we've been building computer-use agents
that have been used by various teams for QA testing, but realized
that the underlying browsing frameworks aren't quite good enough
yet. As such, we've been working on a browsing agent. We achieved
72.7% on WebArena compared to the previous state of the art set by
OpenAI's new ChatGPT agent at 65.4%. You can read more about it
here: https://github.com/trymeka/webarena_evals. Today, we are
open sourcing Meka, our state of the art agent, to allow anyone to
build their own powerful, vision-based agents from scratch. We
provide the groundwork for the hard parts, so you don't have to: *
True vision-based control: Meka doesn't just read HTML. It looks at
the screen, identifies interactive elements, and decides where to
click, type, and scroll. * Full computer access: It's not
sandboxed in a browser. Meka operates with OS-level controls,
allowing it to handle system dialogues, file uploads, and other
interactions that browser-only automation tools can't. *
Extensible by design: We've made it easy to plug in your own LLMs
and computer providers. * State-of-the-art performance: 72.7% on
WebArena Our goal is to enable developers to create repeatable,
robust tasks on any computer just by prompting an agent, without
worrying about the implementation details. We'd love to get your
feedback on how this tool could fit into your automation workflows.
Try it out and let us know what you think. You can find the repo
on GitHub and get started quickly with our hosted platform,
https://app.withmeka.com/. Thanks, Winston, Edward, and James
Author : ElasticBottle
Score : 36 points
Date : 2025-07-30 14:11 UTC (8 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| cahoodle wrote:
| James here from the team! Let us know if you have feedback on
| either our cloud or open source repo. We want to push the
| frontiers for computer-use so that people can do less repetitive
| work.
| hugs wrote:
| that yc app deadline is just around the corner, isn't it? :)
| cahoodle wrote:
| Didn't even realize, maybe we'll put in an app!
|
| I did YC back in S16 and was just reminiscing with a friend
| about how startups felt so different back then.
| phsource wrote:
| This is pretty impressive results given that this is not from
| one of the major AI labs. Congrats:
| https://blog.withmeka.com/meka-achieves-state-of-the-art-per...
|
| Out of curiosity, what do you think contributed to this working
| better than even OpenAI agent or some of the other tools out
| there?
|
| I'm not that familiar with how OpenAI and other agents like
| Browser Use currently work, but is this, in your opinion, the
| most important factor?
|
| > An infrastructure provider that exposes OS-level controls,
| not just a browser layer with Playwright screenshots. This is
| important for performance as a number of common web elements
| are rendered at the system level, invisible to the browser page
| tcwd wrote:
| Thanks! Quite a few factors, here's a detailed post on the
| architecture: https://blog.withmeka.com/introducing-meka-an-
| open-source-fr...
|
| IMO, the combination of having an "evaluator model" at the
| end to verify if the intent of the task was complete, and
| using multiple models that look over each other's work in
| every step was helpful - lots of human organization analogies
| there, like "trust but verify" and pair programming. Memory
| management was also very key.
| anonymousiam wrote:
| "* Full computer access: It's not sandboxed in a browser. Meka
| operates with OS-level controls, allowing it to handle system
| dialogues, file uploads, and other interactions that browser-only
| automation tools can't."
|
| This seems pretty scary. Just recently an AI wiped a company
| database: https://fortune.com/2025/07/23/ai-coding-tool-replit-
| wiped-d...
| xnx wrote:
| Power and risk go hand in hand. Best approach is probably to
| run in a VM.
| ElasticBottle wrote:
| Yeap, that's exactly where the agents run in
| tcwd wrote:
| Hi there, I'm Edward, one of the co-founders. The OS that the
| agent operates in is a fresh confined environment, and not a
| company or personal computer.
| wsycharles0o wrote:
| I would assume this capability is meant to be used in a docker?
| tcwd wrote:
| We explored using a containerized VM that exposed agentic
| controls in the open source version, but generally found that
| the cloud-based solutions were much faster to get started and
| easier to work with. Our repo contains adapters that work
| with several of the most popular cloud-hosted VM-as-a-service
| infra providers.
|
| Definitely would be happy to be wrong and missed something
| here!
___________________________________________________________________
(page generated 2025-07-30 23:00 UTC)