Instead of migrating from server to server — and remaining on computers I don’t own - I download locally which it looks this tool doesn’t do. I use mbsync/isync which is fast and reliable. https://isync.sourceforge.io/. - Source: Hacker News / over 1 year ago

There are also isync and OfflineIMAP which sync email locally. Source: about 3 years ago

I set up mbsync to mirror the current (last 90 days) of my Fastmail IMAP account into another local Maildir, and told Notmuch to index that as well. This ensures a Notmuch search will cover both current & archived messages. Source: over 3 years ago

On my notebook I went full-on nerd and read and write emails mostly in the Emacs text editor. In particular I use isync to fetch emails via imap (that's independent from Emacs) and the Emacs extension mu4e to view, write and send emails. It's not something I recommend if you're not used to working with code and not using Emacs anyway, but for me it makes sense, since emails are just text and Emacs is good with... Source: over 3 years ago

Myself, I keep a local copy of my mail using isync/mbsync. This allows me to use mutt and notmuch on my mail, or even just plain old grep. Granted, this also means you'll have to download your 30GB mailbox locally. Personally, I consider this a feature, as it gives me a local backup. Source: over 3 years ago

This is usually a challenge that any developer has to take care of when building an AI agent. In fact, managing the context is one of the hardest problems when working with AI agents and there are many companies like SuperMemory, Mem0 which have invested both resources and time to solve this problem. - Source: dev.to / 15 days ago

Memory. I use Supermemory for this. Before, Pipa loaded context files and knew to update them. A memory tool adds teammate-like recall: goals, preferences, latest business state, and small details that should carry across runs. Good memory tools also know how to supersede and delete memories, which matters once the agent has more autonomy. - Source: dev.to / about 2 months ago

We wire everything up with Vision Agents as the voice agent framework, Stream for WebRTC audio and video, OpenAI Realtime for speech in and speech out, Anam so the agent shows up as a face on the video, and Supermemory so answers come from search over your uploaded documents instead of guesswork. The code stays small and most of the behavior lives in one registered function that asks the memory store for relevant... - Source: dev.to / 3 months ago

My friends and I are working on https://supermemory.ai, an AI second brain to help you remember content from saved webpages and notes. - Source: Hacker News / almost 2 years ago