Basil Yaqoob

Hey everyone starting this thread as an open space for anything Ollie-related: how a connector works, why we made a certain call (like running everything locally instead of in the cloud), what's still missing, or just general feedback after trying it out.

A few things people tend to ask, to save you a search:

• How's this different from just using ChatGPT with plugins? Ollie connects directly to Gmail, Outlook, Slack, QuickBooks and many more via MCP and can actually take action (send an email, draft a reply, pull real numbers) - always showing you what it's about to do before it does it.

• Where does my data go? Nowhere but your own machine. Ollie runs as a desktop app with a local database - no cloud sync of your inbox or financials.

• What's next? More connectors, and continued work on making the memory smarter the longer you use it.

If you hit a bug, have a feature you wish existed, or just want to know how something under the hood works drop it here. I'm reading every reply.

Cloudflare put out an open-source project called Cloudflare OS a week or so ago, and the part that caught my attention is "Gatekeepers": a capability-based layer that requires async approval before an agent can take a sensitive action. It got a lot of attention on HN specifically for that idea, more than the platform itself.

I've been dealing with a version of this same problem: figuring out where the line is between actions an agent should just do versus actions that need a human to say yes first. The "async" part is what's interesting to me. Most approval flows I've seen block the whole turn until someone responds. Doing it asynchronously means the agent can keep working on other things while one action sits waiting.

Curious if anyone's actually wired this into a real workflow yet, and whether async approval ends up feeling smoother in practice or just adds a different kind of complexity (tracking what's pending, handling timeouts, etc).