I work on geospatial apps and the software I think I am most excited about is https://felt.com/. I want to seem them expand their tooling such that maps and data source authentication/authorization was controllable by the developer, to enable tenant isolation with propriety data access. They could really disrupt how geospatial tech gets integrated into consumer apps. This article doesn't acknowledge how niche this... - Source: Hacker News / over 1 year ago

Felt | Senior Infrastructure Engineer, Growth Product Manager | Oakland, CA or REMOTE (US only) | Full Time | https://felt.com Felt is building a cloud-based geographic information systems (GIS) solution and have hundreds of customers already using it to run their operations, processing terabytes of data. Our team hails from Uber, Google, Meta, CARTO, Mapbox, The New York Times and a few others. If you have used... - Source: Hacker News / over 1 year ago

How does this compare to Felt [1]? It would be nice to have some plans with listed prices in between "Free" and "Enterprise" ("book a demo"). For comparison, Felt has $30/mo and $90/mo plans. Calling yourselves "the new standard for GIS software" seems like overly strong branding. [1]: https://felt.com/. - Source: Hacker News / over 2 years ago

Felt | Engineering Manager, App and Data | Oakland, CA or REMOTE (US timezones) | Full Time | https://felt.com Felt is the best way to make maps on the internet. It's surprisingly hard to make a map today, and people in 15+ industries rely on them to do their jobs. Climate change and the resulting natural disasters are forcing even more people to become map-makers, and Felt is here to meet that need. It's the... - Source: Hacker News / over 2 years ago

For anyone else who follows along in this domain, there's an interesting competitor in the space I stumbled across recently: https://felt.com/ Pretty nice looking product and robust feature set. Love to see GIS tooling becoming more accessible. - Source: Hacker News / almost 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 / 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 / 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