Umfeld.App Early Beta Launch
Give your AI a memory for people.
What it does
Umfeld is a personal CRM built MCP-first: it turns your Google Contacts into a living relationship graph and hands it to Claude, ChatGPT, or any MCP client. Unlike classic personal CRMs, your AI can read and write it ask "who have I lost touch with?", log a coffee by voice, get nudges from a relationship health score before people cool off. Hosted in Germany. For friends, family and your network, no pipelines, no deals.
Umfeld turns your Google Contacts into a living relationship graph for Claude, ChatGPT and any MCP client. Ask who's worth reaching out to — never lose touch.
Umfeld turns your Google contacts into a living relationship graph, then hands it to Claude, ChatGPT, and any MCP client. Ask who's worth reaching out to. It already knows. Three people you were close to have gone quiet. Worth a hello: Umfeld sits between your address book and your assistant: a single MCP server that any model can read from and write to. Link Google Contacts in a click. Forward an email, snap a business card, or just speak a name. Umfeld fills in the rest. Every person becomes a node in a relationship graph: who they are, how you met, when you last spoke, and how warm it is. Through MCP, your assistant reads and writes the graph. It drafts the message, logs the note, and…from umfeld.app
Does the same job
all alternatives →
- MCMicro CRM, a CRM for People Who Hate CRMs2019 · ▲147
Hello Community! My name is Charles-Eugene Loubao, I am a software developer who recently turned into an Indie Maker and I am sharing my new product with you today. Micro CRM is a Customer Relationship Managment web app built to be easy to use and intuitive. Most CRMs can be complicated to use and come with an expensive price tag. Micro CRM is built to fill that need for a much simpler and cheaper contact managment platform that offers compeling features without being overwhelming. What can I do with it ? - Keep all your contacts in one place - Timestamped notes can be used to keep track of…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com