Hacker news

  • Top
  • New
  • Past
  • Ask
  • Show
  • Jobs

OpenCode Browse (https://opencode.ai)

334 points by mfiguiere 4 days ago | 222 comments | View on ycombinator

testtestmetest 4 days ago |

Opencode vibe codes and releases like 3 projects a week at this points. Cool, just know its throwaway software to them. They seem really reckless when it comes to security. Opencode V2 basically threw security out the window. Theyve completely lost the plot as an org.

Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious

Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to control the browser at a low level.

If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod.

jeremyjacob 4 days ago |

The functionality seems to overlap with the Playwright MCP server [0]. I've been using this instead of the built in browsers in Claude Code and Codex since it lets you grant access to pages and sessions that are already open. Of course one should be weary of the lethal trifecta when using these tools and use separate profiles for them.

[0] https://playwright.dev/docs/getting-started-mcp

eatfish 3 days ago |

I keep asking my own agents if prompt injection is a solved problem. By and large the answer seems to be ‘no, anything a model sees can be used to steer it and enters the context’.

I know you can forward raw output through subagents to summarize content and mitigate the risk - but most projects don’t do that.

So why would anyone risk browser or email to agents where your secrets are at their most vulnerable. Serious question, looking for someone who knows this stuff and can reassure me (or not) on the real risks.

tornikeo 3 days ago |

Browse is good. Been using it for 2 weeks now.

- Allows agents interacting with tabs without focusing screen on them

- Works as CLI and as MCP (I use cli)

- Works on a chromium, brave, chrome

- can switch between chromium profiles and browsers

- No bugs encountered whatsoever, and I use it heavily.

Would highly recommend.

sixtyj 4 days ago |

> Your real browser: Chrome, Edge, Brave, Arc, Helium, Vivaldi, Opera and Chromium.

Firefox not?

SillyUsername 3 days ago |

MCP servers to me seems like a dead man walking technology and I don't understand the point of it.

It adds security but...

- adds a single service which is another attack surface that can be compromised.

- adds another system that requires maintenance and securing to prevent compromise.

- takes machine resources

- duplicates a subset of what can easily be harness functionality

- duplicates services and security (usually) of existing APIs, or adds another layer on top.

Whereas ultimately an AI harness

- will improve and optimise its own skills performing the same MCP functions

- can use plugins

- can have harness centralised (common) security controls and behaviours

MCP becomes a false economy for our current AI implementations, it's real purpose seems to be a crutch for small models that struggle to write their own skills that use existing APIs. The thing is this is a problem that is rapidly disappearing, but could also be performed by secured harness plugins.

bita_nidir 3 days ago |

I'm definitely checking this out, thanks!

I know I should never look a gift horse in the mouth, but it would be cracking to have Firefox support in this too, wink, wink :)

_pdp_ 4 days ago |

Cool.. but I think it is just simply better to give your AI agents their own browsers for your own sanity.

NishanStepak 3 days ago |

I have been using Open Code with Big Pickle, basically I have downloaded it to my desktop and used it with a local host. So far it has cost me nothing. It is a way to do things for very little money. I have run out of time a couple time, but I just go for the next. I don't even look at X or Twitter.

gitgud 3 days ago |

Nice, this seems to directly compete with the Anthropic Claude extension which has currently has 23 million user's

https://chromewebstore.google.com/detail/claude/fcoeoabgfene...

kristopolous 3 days ago |

I was just looking into these "chat with ai agent about a webpage" browser extensions/projects/forks ... can someone help me sort out this field? it seems really busy.

What I really want is like something that can search, use my own openai compatible server with, and I think that's it? I dunno what else these things do.

int32max 3 days ago |

I have been using opencode for quite along time even before they had an official ios port and think it's the most flexible harness for the best bang for your buck. 10 quid with practicality unlimited usage for side projects and personal agent stuff.

They ship a lot but the quality is insanely high.

apatap 3 days ago |

That looks cool! I've been doing something similar by having opencode launch Chrome with a remote debug port.

I'd love to know how this approach compares. Does it help save on tokens, or are the safety guardrails handled differently?

0xbadcafebee 3 days ago |

You can implement this as a skill in any AI agent in about 5 minutes, just ask it to make this and it will. I've done this with Chrome and Firefox five different ways, not counting MCP and pre-existing extensions. I basically have one skill that calls four different browser skills depending on how hardcore the bot detection is. New browser profile each session. 1Password and a custom app let me prompt for auth on any machine.

Tangent: Xvfb makes it crazy easy to implement headless computer use for any app. Add SSH or VNC for remote access. Open weights easily use the x11 tools to control the GUIs, makes testing and automation a breeze.

regexorcist 3 days ago |

Opencode has a lot of issues and I've tried all the alternatives but ultimately it's the one I go back to. You have to treat it like untrusted code full of telemetry and data leaks like the infamous title generations. Ask your agent to craft a config disabling everything, and then run it in a sandbox without direct network access with a proxy for whitelisted domains. But that applies to any agent really. The tabs in the v2.0 TUI are a game changer for me so it looks like I'll keep using it for now.

FooBarWidget 3 days ago |

What do people use products like this for, and how do you reconcile security concerns? Personally, all of the use cases I want to use such a products for, can't tolerate security failures. For example I would love if an agent can download invoices for me (super annoying and low-value recurring work) but if they can download my invoices then they can also delete my account.

rolosa 3 days ago |

What self hosted batteries included api/mcp can an agent control that also gets around bot blocks like Amazon.com with the ability to hand off the webpage to me on my iPhone to approve/login/purchase stuff? I've been using muse and like how they built the browser for it but too many websites block the data center ip and fingerprinting.

kzahel 3 days ago |

Looks cool. I slopped something similar but with also full desktop control in addition to the browser debugger extension. Because I was not satisfied with openai computer use being limited and refusing to interact with menu bar/task tray. https://machinecontrol.dev/ Use it daily with Claude and codex.

MIT license.

latchkey 4 days ago |

codex's extension connection will often randomly fail on me and i (and ai) can't figure out how to get it working again.

i've switched to using omp's extension and that seems to work better.

https://github.com/can1357/oh-my-pi/blob/main/packages/brows...

esafak 4 days ago |

It's all right when it works, but it has a habit of disconnecting; you have to rerun 'browse pair'. This MCP should hopefully become unnecessary once OpenCode's integrated browser tool gains persistent sessions. https://github.com/anomalyco/opencode/pull/63002

theanonymousone 3 days ago |

My "agents" already do that, directly on macOS and via CDP on Linux. How is this different?

sans_souse 3 days ago |

Check out https://opencode.ai/robots.txt for a treat

breakwaterlabs 4 days ago |

At least they don't even pretend that it's sandboxed or approval gated.

To anyone trying this, good luck and keep a fire extinguisher handy.

bob1029 3 days ago |

I don't understand the need for this. A strong reasoning model already knows how to use Powershell to launch my browser with my profile. gpt-6.1-terra will build a whole goddamn .NET project with playwright just to pull the showtimes from the local cineplex.

Shell execute and apply patch are the only two tools you need if your reasoning model is powerful enough.

mrtksn 3 days ago |

Funny, I just vibecoded a Chrome extension that does exactly that for my agent harness. I wonder if at OpenAI they too just told GPT “Let’s create a browser and Chrome extension for browser use, when done publish it on our website and post it to HN”. Because the agent itself is the user it worked until it’s happy fulfilling my request, modifying and adding functions when itself needs.

keyle 3 days ago |

You had me, until "... your logins and your extensions".

It's like open doors at a virus research facility.

forgotpwd16 3 days ago |

Looks great, but us poor Firefox users are left staring through the window while Chrome gets to browse. Any chance of Firefox support?

edit: Heh, nice. Previous was sent by OC Browse. Prompted find story, and write comment.

vibebingo 4 days ago |

Oh this is a problem? I just ask my agent to do stuff with a browser and it figures it out.

vovavili 3 days ago |

This is promising. My primary use of Codex is browser automation, and I perpetually keep running out of tokens for menial tasks. OpenCode + Spark Muse will make my life so much easier.

skeledrew 4 days ago |

I found agent browsing to be an issue when I started using them months ago. Built a Firefox extension back then that uses the browser instance that I use, the way I use it, so there's really no difference to a site.

voxelghost 3 days ago |

What could possibly go wrong

hendrikmans 3 days ago |

They've had so many security incidents I wouldn't even put this on my enemy's computer.

hank2000 3 days ago |

Are folks using opencode over say… openhands? Or pi?

orsenthil 4 days ago |

OpenCode comes with the cost too. The cost of the hosted version is on par with cloud hosted proprietary models. And we cannot simply run the LLMs on every laptop. Given this, how do we us the browse efficiently?

undefined 3 days ago |

undefined

orliesaurus 3 days ago |

as much of a non-vercel fanboy I am, I think agent-browser by vercel is where it's at these days

devkumardev2001 about 23 hours ago |

[flagged]

akhrienov 3 days ago |

[flagged]

everest_e 3 days ago |

[flagged]

aeswibon 3 days ago |

[flagged]

bill10 3 days ago |

[flagged]

tha_infra_guy 3 days ago |

[flagged]