Web Store extensions unfortunately don't work in Ungoogled Chromium. There is a a way around it however. It requires a website that fetches the extension file. Source: over 3 years ago

Yeah, that's definitely a downside to creating Chrome extensions for constantly changing sites. However, you could implement checks that notify you quickly of any breaking changes. I don't have the code hosted publicly on GitHub, but you can use sites like this one to obtain it. The code for this extension is not obfuscated. Source: over 3 years ago

Go to https://crxextractor.com/ and use the link from the downloadhelper download page (https://chrome.google.com/webstore/detail/video-downloadhelper/lmjnegcaeklhafolokijcfjliaokphfk) download the crx and then go to brave://extensions/ and enable developer mode and drag and drop the crx file. Source: over 3 years ago

Chrome extensions are written in Javascript. In fact, you can look at the full source code for any Chrome extension you want - you can find where it's downloaded on your computer (~/Library/Application Support/Google/Chrome/Default/Extensions for Mac) or you can use a website like this to download it. Source: over 3 years ago

P.S. You can always grab the code from https://crxextractor.com it’s a bit messy, but thats my style of coding :). 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 / about 1 month 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 / 3 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 / 4 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 / about 2 years ago