Maybe you would be interested in Waydroid too https://waydro.id/. - Source: Hacker News / 8 months ago

Probably Waydroid [1]. It's been around for a while and apparently works very well. [1] https://waydro.id. - Source: Hacker News / 9 months ago

Maybe the real focus should be treating Android as a single purpose environment rather than your real/life depending one. Maybe the better approach would be focusing on getting postmarketOS to work, and use an emulation or recompilation layer that is running Android in a box (pun intended). Anbox and others were still too painful to use for daily usage, but maybe you can get rid of everything except the things... - Source: Hacker News / 10 months ago

Yep, and in the reverse, you don't need a separate kernel to run Android software on Linux: https://waydro.id. - Source: Hacker News / about 1 year ago

In theory you have the likes of the PinePhone where you can run a full Linux kernel [1]. You could then use something like Waydroid to run Android apps [2]. I think the biggest concern is that many of the important apps are anti-emulation, for example banking apps and authentication apps. [1] https://pine64.org/devices/pinephone_pro/ [2] https://waydro.id/. - Source: Hacker News / over 1 year 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 / 17 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