You should open the issue with your IT department and see if they can optimize the performance. You can gather proof that GoGuardian is causing slow downs by looking at it's memory usage in the Task Manager (right click empty area in Chrome tab bar).

The knowledge graph is well done. I think what's missing from all coworking apps is the UX.

Prompting is a very specialized skill, average users just don't know what to ask for to get the most out of the LLMs.

Ideally the UX should organize and surface information to the user that is important automatically, without needing to be prompted.

Thanks, completely agree. UX is probably the hardest part here. Prompting should not be a prerequisite for getting value. We have been thinking about making the system more proactive, for example surfacing relevant notes ahead of meetings or highlighting changes that need attention. Would love to hear how you think this should ideally work.

I'd be happy to meet and discuss. I will reach out.

Great, looking forward to it.

/sandbox https://code.claude.com/docs/en/sandboxing

> The sandboxed bash tool uses OS-level primitives to enforce both filesystem and network isolation.

As I can't trust Claude Code to use a correct shell, I don't know why I would trust this feature.

Note that there are reports that it can disable sandbox, so personally I wouldn't trust this.

We use https://devin.ai for this and it works very well. Devin has it's own virtual environment, IDE, terminal and browser. You can configure it to run your application and connect to whatever it needs. Devin can modify the app, test changes in the browser and send you a screen recording of the working feature with a PR.

Interestingly, Devin lists Ramp (the OP) as a customer on their front page.

Surprised they need both.

Why is OpenCode better than Claude Code?

I wouldn’t say it’s better, but it does have some nice features. Opencode has a web UI, so I can open it on my laptop and then resume the same session on the web from my phone through Tailscale. It’s pretty handy from time to time and takes almost zero effort from me.

Works with several providers (e.g. Github copilot or bring your own key). They offer a server and an sdk, so you can build all kinds of personal tools. It's amazing.

Claude Code also has Claude Agent SDK (basically a wrapper around Claude Code) with a million downloads in the past week.

https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk

Very interesting! What do you mean by personal tools? Do you have any examples of something you've built with this?

It is open source, to start with, and works with a lot of LLMs providers instead of being vendor locked into one.

Nice solution, I had some success with https://www.task-master.dev/ it's a bit more complex though

For connecting agents to third-party systems I prefer CLI tools, less context bloat and faster. You can define the CLI usage in your agent instructions. If the MCP you're using doesn't exist as a CLI, build one with your agent.

Totally agree - wrote this over the holidays which sums it all pretty well https://martinalderson.com/posts/why-im-building-my-own-clis...

Well kind of. They use the same data center infrastructure, with internal versions of the external GCP services.

Depends on the service but for the most part googles infra has its own stack that GCP is built on top of. There is always initiatives going on to get more internal stuff running on GCP as opposed to the internal infra directly, but none of them have really stuck that I saw.

I'm fairly new to Docker. Do folks really rely on public images and registries for production systems? Seems like a brittle strategy.

Yes, 1000s of orgs. Larger players might use a pull-through-cache - but it's not as common as it should be. Similar issue for other software-supply-chain (NPM, pyPi, etc)

Built something similar and it worked quite well. Gemini Flash models are very performant and low cost for these types of solutions.